{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402085304260254, "min": 1.402085304260254, "max": 1.425513505935669, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 69333.1171875, "min": 68694.234375, "max": 78379.7734375, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.8037542662116, "min": 73.90854572713643, "max": 420.83193277310926, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49695.0, "min": 49276.0, "max": 50152.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999949.0, "min": 49498.0, "max": 1999949.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999949.0, "min": 49498.0, "max": 1999949.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4822633266448975, "min": 0.12839633226394653, "max": 2.489129066467285, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1454.6063232421875, "min": 15.150766372680664, "max": 1641.3856201171875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.8746108110650814, "min": 1.7528293135307602, "max": 3.9877712503665976, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2270.5219352841377, "min": 206.83385899662971, "max": 2586.9908241033554, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.8746108110650814, "min": 1.7528293135307602, "max": 3.9877712503665976, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2270.5219352841377, "min": 206.83385899662971, "max": 2586.9908241033554, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017099774852411227, "min": 0.013298253097066965, "max": 0.021073890907185464, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.051299324557233676, "min": 0.02659650619413393, "max": 0.05633551016095832, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05921612228784296, "min": 0.023048129367331666, "max": 0.06471971559027831, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.1776483668635289, "min": 0.04609625873466333, "max": 0.185767646258076, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.530048823350004e-06, "min": 3.530048823350004e-06, "max": 0.0002952532515822499, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0590146470050012e-05, "min": 1.0590146470050012e-05, "max": 0.0008434953188348997, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10117665000000002, "min": 0.10117665000000002, "max": 0.19841775, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30352995000000005, "min": 0.20747910000000003, "max": 0.5811651, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 6.871483500000009e-05, "min": 6.871483500000009e-05, "max": 0.004921045724999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00020614450500000024, "min": 0.00020614450500000024, "max": 0.01406013849, "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": "1683868050", "python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1683870408" }, "total": 2358.172158946, "count": 1, "self": 0.4346102329996029, "children": { "run_training.setup": { "total": 0.04072347100003526, "count": 1, "self": 0.04072347100003526 }, "TrainerController.start_learning": { "total": 2357.696825242, "count": 1, "self": 4.215846576862077, "children": { "TrainerController._reset_env": { "total": 3.8860177500000077, "count": 1, "self": 3.8860177500000077 }, "TrainerController.advance": { "total": 2349.4694897871377, "count": 233319, "self": 4.320507208039999, "children": { "env_step": { "total": 1825.6879131570865, "count": 233319, "self": 1541.36429839319, "children": { "SubprocessEnvManager._take_step": { "total": 281.5672972799272, "count": 233319, "self": 16.13603422685628, "children": { "TorchPolicy.evaluate": { "total": 265.4312630530709, "count": 222981, "self": 265.4312630530709 } } }, "workers": { "total": 2.7563174839694966, "count": 233319, "self": 0.0, "children": { "worker_root": { "total": 2349.9521683209596, "count": 233319, "is_parallel": true, "self": 1088.7422976929793, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0008625610000194683, "count": 1, "is_parallel": true, "self": 0.0002535269999839329, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006090340000355354, "count": 2, "is_parallel": true, "self": 0.0006090340000355354 } } }, "UnityEnvironment.step": { "total": 0.028569788000027074, "count": 1, "is_parallel": true, "self": 0.00030101700002660436, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00024506599999085665, "count": 1, "is_parallel": true, "self": 0.00024506599999085665 }, "communicator.exchange": { "total": 0.027338801000041713, "count": 1, "is_parallel": true, "self": 0.027338801000041713 }, "steps_from_proto": { "total": 0.0006849039999679007, "count": 1, "is_parallel": true, "self": 0.00022295899992741397, "children": { "_process_rank_one_or_two_observation": { "total": 0.0004619450000404868, "count": 2, "is_parallel": true, "self": 0.0004619450000404868 } } } } } } }, "UnityEnvironment.step": { "total": 1261.2098706279803, "count": 233318, "is_parallel": true, "self": 38.3807992539364, "children": { "UnityEnvironment._generate_step_input": { "total": 77.47033529199012, "count": 233318, "is_parallel": true, "self": 77.47033529199012 }, "communicator.exchange": { "total": 1052.819346447031, "count": 233318, "is_parallel": true, "self": 1052.819346447031 }, "steps_from_proto": { "total": 92.53938963502299, "count": 233318, "is_parallel": true, "self": 34.15067599100689, "children": { "_process_rank_one_or_two_observation": { "total": 58.38871364401609, "count": 466636, "is_parallel": true, "self": 58.38871364401609 } } } } } } } } } } }, "trainer_advance": { "total": 519.4610694220114, "count": 233319, "self": 6.263235523985713, "children": { "process_trajectory": { "total": 135.13553668202576, "count": 233319, "self": 133.67031370102586, "children": { "RLTrainer._checkpoint": { "total": 1.4652229809998971, "count": 10, "self": 1.4652229809998971 } } }, "_update_policy": { "total": 378.062297216, "count": 97, "self": 318.5140867679997, "children": { "TorchPPOOptimizer.update": { "total": 59.548210448000304, "count": 2910, "self": 59.548210448000304 } } } } } } }, "trainer_threads": { "total": 9.73000169324223e-07, "count": 1, "self": 9.73000169324223e-07 }, "TrainerController._save_models": { "total": 0.12547015500013003, "count": 1, "self": 0.002246288000151253, "children": { "RLTrainer._checkpoint": { "total": 0.12322386699997878, "count": 1, "self": 0.12322386699997878 } } } } } } }