{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.402813196182251, "min": 1.402813196182251, "max": 1.4272922277450562, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70106.9921875, "min": 67885.1171875, "max": 78319.3125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 84.85540069686411, "min": 81.11822660098522, "max": 419.19166666666666, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 48707.0, "min": 48707.0, "max": 50303.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999956.0, "min": 49790.0, "max": 1999956.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999956.0, "min": 49790.0, "max": 1999956.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.4303476810455322, "min": 0.15938083827495575, "max": 2.509798765182495, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1397.449951171875, "min": 18.966320037841797, "max": 1513.8768310546875, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.753478131605231, "min": 1.897657567713441, "max": 3.97343139334618, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2158.249925673008, "min": 225.82125055789948, "max": 2331.0211389660835, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.753478131605231, "min": 1.897657567713441, "max": 3.97343139334618, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2158.249925673008, "min": 225.82125055789948, "max": 2331.0211389660835, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.017542432476249006, "min": 0.013167783810179873, "max": 0.01999284463818185, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.052627297428747014, "min": 0.026335567620359747, "max": 0.05660752055312818, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.06069977813296848, "min": 0.020472330910464125, "max": 0.06069977813296848, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.18209933439890544, "min": 0.04094466182092825, "max": 0.18209933439890544, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.7271987576333377e-06, "min": 3.7271987576333377e-06, "max": 0.00029536245154585, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.1181596272900013e-05, "min": 1.1181596272900013e-05, "max": 0.00084407806864065, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10124236666666668, "min": 0.10124236666666668, "max": 0.19845415000000008, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.3037271, "min": 0.20763020000000004, "max": 0.58135935, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.199409666666677e-05, "min": 7.199409666666677e-05, "max": 0.004922862084999999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021598229000000028, "min": 0.00021598229000000028, "max": 0.014069831565000001, "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": "1677826546", "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": "1677829091" }, "total": 2544.381329444, "count": 1, "self": 0.4397814650001237, "children": { "run_training.setup": { "total": 0.11346896200001311, "count": 1, "self": 0.11346896200001311 }, "TrainerController.start_learning": { "total": 2543.828079017, "count": 1, "self": 4.49633737296017, "children": { "TrainerController._reset_env": { "total": 10.192443646999948, "count": 1, "self": 10.192443646999948 }, "TrainerController.advance": { "total": 2529.03008423004, "count": 232475, "self": 4.9418382311246205, "children": { "env_step": { "total": 1972.3102413570114, "count": 232475, "self": 1649.7613659850465, "children": { "SubprocessEnvManager._take_step": { "total": 319.60363437392414, "count": 232475, "self": 17.012949197860735, "children": { "TorchPolicy.evaluate": { "total": 302.5906851760634, "count": 222989, "self": 75.87337881610222, "children": { "TorchPolicy.sample_actions": { "total": 226.71730635996119, "count": 222989, "self": 226.71730635996119 } } } } }, "workers": { "total": 2.945240998040731, "count": 232475, "self": 0.0, "children": { "worker_root": { "total": 2535.1377635780213, "count": 232475, "is_parallel": true, "self": 1197.8150087019726, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.0010571869999580485, "count": 1, "is_parallel": true, "self": 0.0004010869999433453, "children": { "_process_rank_one_or_two_observation": { "total": 0.0006561000000147033, "count": 2, "is_parallel": true, "self": 0.0006561000000147033 } } }, "UnityEnvironment.step": { "total": 0.033754301000044507, "count": 1, "is_parallel": true, "self": 0.00033843500000330096, "children": { "UnityEnvironment._generate_step_input": { "total": 0.00023110800003678378, "count": 1, "is_parallel": true, "self": 0.00023110800003678378 }, "communicator.exchange": { "total": 0.030606949000002714, "count": 1, "is_parallel": true, "self": 0.030606949000002714 }, "steps_from_proto": { "total": 0.0025778090000017073, "count": 1, "is_parallel": true, "self": 0.00039709699996137715, "children": { "_process_rank_one_or_two_observation": { "total": 0.00218071200004033, "count": 2, "is_parallel": true, "self": 0.00218071200004033 } } } } } } }, "UnityEnvironment.step": { "total": 1337.3227548760487, "count": 232474, "is_parallel": true, "self": 39.38093851478948, "children": { "UnityEnvironment._generate_step_input": { "total": 85.13134265409457, "count": 232474, "is_parallel": true, "self": 85.13134265409457 }, "communicator.exchange": { "total": 1117.652396641054, "count": 232474, "is_parallel": true, "self": 1117.652396641054 }, "steps_from_proto": { "total": 95.15807706611054, "count": 232474, "is_parallel": true, "self": 40.6927535691222, "children": { "_process_rank_one_or_two_observation": { "total": 54.46532349698833, "count": 464948, "is_parallel": true, "self": 54.46532349698833 } } } } } } } } } } }, "trainer_advance": { "total": 551.7780046419041, "count": 232475, "self": 6.727390398930652, "children": { "process_trajectory": { "total": 178.01802080397084, "count": 232475, "self": 176.71076990596993, "children": { "RLTrainer._checkpoint": { "total": 1.307250898000916, "count": 10, "self": 1.307250898000916 } } }, "_update_policy": { "total": 367.0325934390026, "count": 97, "self": 308.87235727601194, "children": { "TorchPPOOptimizer.update": { "total": 58.16023616299066, "count": 2910, "self": 58.16023616299066 } } } } } } }, "trainer_threads": { "total": 8.629999683762435e-07, "count": 1, "self": 8.629999683762435e-07 }, "TrainerController._save_models": { "total": 0.10921290400028738, "count": 1, "self": 0.002158216000225366, "children": { "RLTrainer._checkpoint": { "total": 0.10705468800006201, "count": 1, "self": 0.10705468800006201 } } } } } } }