{ "name": "root", "gauges": { "Huggy.Policy.Entropy.mean": { "value": 1.4074827432632446, "min": 1.4074827432632446, "max": 1.4285556077957153, "count": 40 }, "Huggy.Policy.Entropy.sum": { "value": 70003.96875, "min": 69261.875, "max": 76662.03125, "count": 40 }, "Huggy.Environment.EpisodeLength.mean": { "value": 81.29304635761589, "min": 81.29304635761589, "max": 405.43548387096774, "count": 40 }, "Huggy.Environment.EpisodeLength.sum": { "value": 49101.0, "min": 48856.0, "max": 50274.0, "count": 40 }, "Huggy.Step.mean": { "value": 1999938.0, "min": 49863.0, "max": 1999938.0, "count": 40 }, "Huggy.Step.sum": { "value": 1999938.0, "min": 49863.0, "max": 1999938.0, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.mean": { "value": 2.413158893585205, "min": 0.06357457488775253, "max": 2.4889261722564697, "count": 40 }, "Huggy.Policy.ExtrinsicValueEstimate.sum": { "value": 1462.374267578125, "min": 7.819672584533691, "max": 1462.374267578125, "count": 40 }, "Huggy.Environment.CumulativeReward.mean": { "value": 3.7099732121225237, "min": 1.7809921183237216, "max": 4.00607226097887, "count": 40 }, "Huggy.Environment.CumulativeReward.sum": { "value": 2248.2437665462494, "min": 219.06203055381775, "max": 2263.1318060159683, "count": 40 }, "Huggy.Policy.ExtrinsicReward.mean": { "value": 3.7099732121225237, "min": 1.7809921183237216, "max": 4.00607226097887, "count": 40 }, "Huggy.Policy.ExtrinsicReward.sum": { "value": 2248.2437665462494, "min": 219.06203055381775, "max": 2263.1318060159683, "count": 40 }, "Huggy.Losses.PolicyLoss.mean": { "value": 0.016736365075727615, "min": 0.014144914484738062, "max": 0.020535371990020698, "count": 40 }, "Huggy.Losses.PolicyLoss.sum": { "value": 0.050209095227182844, "min": 0.030483250932108297, "max": 0.059815653421052654, "count": 40 }, "Huggy.Losses.ValueLoss.mean": { "value": 0.05818153661158349, "min": 0.022464406831810873, "max": 0.06182031215478977, "count": 40 }, "Huggy.Losses.ValueLoss.sum": { "value": 0.17454460983475048, "min": 0.044928813663621746, "max": 0.1780934318900108, "count": 40 }, "Huggy.Policy.LearningRate.mean": { "value": 3.6661987779666605e-06, "min": 3.6661987779666605e-06, "max": 0.00029530732656422496, "count": 40 }, "Huggy.Policy.LearningRate.sum": { "value": 1.0998596333899982e-05, "min": 1.0998596333899982e-05, "max": 0.0008438463187179, "count": 40 }, "Huggy.Policy.Epsilon.mean": { "value": 0.10122203333333335, "min": 0.10122203333333335, "max": 0.198435775, "count": 40 }, "Huggy.Policy.Epsilon.sum": { "value": 0.30366610000000005, "min": 0.2075789, "max": 0.5812821, "count": 40 }, "Huggy.Policy.Beta.mean": { "value": 7.097946333333325e-05, "min": 7.097946333333325e-05, "max": 0.004921945172499999, "count": 40 }, "Huggy.Policy.Beta.sum": { "value": 0.00021293838999999974, "min": 0.00021293838999999974, "max": 0.01406597679, "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": "1675213127", "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": "1.21.6", "end_time_seconds": "1675215434" }, "total": 2306.972684537, "count": 1, "self": 0.43762978999984625, "children": { "run_training.setup": { "total": 0.1671187610000402, "count": 1, "self": 0.1671187610000402 }, "TrainerController.start_learning": { "total": 2306.3679359860002, "count": 1, "self": 4.031882575894997, "children": { "TrainerController._reset_env": { "total": 11.147135011000046, "count": 1, "self": 11.147135011000046 }, "TrainerController.advance": { "total": 2291.083530334105, "count": 232363, "self": 4.342702607066258, "children": { "env_step": { "total": 1774.1463892380398, "count": 232363, "self": 1474.267267304049, "children": { "SubprocessEnvManager._take_step": { "total": 297.1378240920199, "count": 232363, "self": 15.459900670995182, "children": { "TorchPolicy.evaluate": { "total": 281.67792342102473, "count": 222918, "self": 68.8864196549876, "children": { "TorchPolicy.sample_actions": { "total": 212.79150376603712, "count": 222918, "self": 212.79150376603712 } } } } }, "workers": { "total": 2.7412978419708907, "count": 232363, "self": 0.0, "children": { "worker_root": { "total": 2298.537688903023, "count": 232363, "is_parallel": true, "self": 1099.6149110259603, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.00209108799998603, "count": 1, "is_parallel": true, "self": 0.00042048400001704067, "children": { "_process_rank_one_or_two_observation": { "total": 0.0016706039999689892, "count": 2, "is_parallel": true, "self": 0.0016706039999689892 } } }, "UnityEnvironment.step": { "total": 0.02714494700001069, "count": 1, "is_parallel": true, "self": 0.0002707519999489705, "children": { "UnityEnvironment._generate_step_input": { "total": 0.000180617000012262, "count": 1, "is_parallel": true, "self": 0.000180617000012262 }, "communicator.exchange": { "total": 0.02583438900001056, "count": 1, "is_parallel": true, "self": 0.02583438900001056 }, "steps_from_proto": { "total": 0.0008591890000388958, "count": 1, "is_parallel": true, "self": 0.0004124320000755688, "children": { "_process_rank_one_or_two_observation": { "total": 0.00044675699996332696, "count": 2, "is_parallel": true, "self": 0.00044675699996332696 } } } } } } }, "UnityEnvironment.step": { "total": 1198.9227778770628, "count": 232362, "is_parallel": true, "self": 33.79130265907111, "children": { "UnityEnvironment._generate_step_input": { "total": 71.96523324295794, "count": 232362, "is_parallel": true, "self": 71.96523324295794 }, "communicator.exchange": { "total": 1004.7940709899722, "count": 232362, "is_parallel": true, "self": 1004.7940709899722 }, "steps_from_proto": { "total": 88.37217098506159, "count": 232362, "is_parallel": true, "self": 36.406620973915494, "children": { "_process_rank_one_or_two_observation": { "total": 51.96555001114609, "count": 464724, "is_parallel": true, "self": 51.96555001114609 } } } } } } } } } } }, "trainer_advance": { "total": 512.5944384889992, "count": 232363, "self": 6.299093360095696, "children": { "process_trajectory": { "total": 162.81159942890503, "count": 232363, "self": 161.4947480069057, "children": { "RLTrainer._checkpoint": { "total": 1.3168514219993313, "count": 10, "self": 1.3168514219993313 } } }, "_update_policy": { "total": 343.4837456999985, "count": 97, "self": 288.4110998899904, "children": { "TorchPPOOptimizer.update": { "total": 55.07264581000811, "count": 2910, "self": 55.07264581000811 } } } } } } }, "trainer_threads": { "total": 9.79000105871819e-07, "count": 1, "self": 9.79000105871819e-07 }, "TrainerController._save_models": { "total": 0.1053870860000643, "count": 1, "self": 0.001967186000001675, "children": { "RLTrainer._checkpoint": { "total": 0.10341990000006263, "count": 1, "self": 0.10341990000006263 } } } } } } }