{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.412305474281311,
"min": 1.412305474281311,
"max": 1.429597020149231,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70901.96875,
"min": 69341.4375,
"max": 77207.921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.22994652406418,
"min": 85.828125,
"max": 399.336,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 48936.0,
"min": 48936.0,
"max": 50026.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999997.0,
"min": 49461.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999997.0,
"min": 49461.0,
"max": 1999997.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.374443531036377,
"min": 0.11057034879922867,
"max": 2.4380249977111816,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1332.0628662109375,
"min": 13.710722923278809,
"max": 1391.2431640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.732119889714076,
"min": 1.8111637902836646,
"max": 3.941910713416412,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2093.7192581295967,
"min": 224.5843099951744,
"max": 2226.135009288788,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.732119889714076,
"min": 1.8111637902836646,
"max": 3.941910713416412,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2093.7192581295967,
"min": 224.5843099951744,
"max": 2226.135009288788,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01693375335817109,
"min": 0.014122477838504385,
"max": 0.01962152680239847,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050801260074513264,
"min": 0.02932030528706188,
"max": 0.058864580407195416,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05216571614146232,
"min": 0.022080424707382917,
"max": 0.05699268914759159,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15649714842438697,
"min": 0.044160849414765835,
"max": 0.1602904123564561,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.598598800499994e-06,
"min": 3.598598800499994e-06,
"max": 0.00029532112655962495,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0795796401499982e-05,
"min": 1.0795796401499982e-05,
"max": 0.0008440393686535502,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011995,
"min": 0.1011995,
"max": 0.19844037500000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035985,
"min": 0.20752179999999998,
"max": 0.58134645,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.985504999999988e-05,
"min": 6.985504999999988e-05,
"max": 0.0049221747125000005,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020956514999999966,
"min": 0.00020956514999999966,
"max": 0.014069187854999998,
"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": "1697422391",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.0.1+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1697424688"
},
"total": 2297.275969906,
"count": 1,
"self": 0.44635789199946885,
"children": {
"run_training.setup": {
"total": 0.04631283500003747,
"count": 1,
"self": 0.04631283500003747
},
"TrainerController.start_learning": {
"total": 2296.783299179,
"count": 1,
"self": 4.190555726072944,
"children": {
"TrainerController._reset_env": {
"total": 7.319743693000021,
"count": 1,
"self": 7.319743693000021
},
"TrainerController.advance": {
"total": 2285.1730506149274,
"count": 231897,
"self": 4.530432405929787,
"children": {
"env_step": {
"total": 1801.216436053042,
"count": 231897,
"self": 1493.7346936890706,
"children": {
"SubprocessEnvManager._take_step": {
"total": 304.81377708093805,
"count": 231897,
"self": 15.837161316922504,
"children": {
"TorchPolicy.evaluate": {
"total": 288.97661576401555,
"count": 222956,
"self": 288.97661576401555
}
}
},
"workers": {
"total": 2.6679652830331975,
"count": 231897,
"self": 0.0,
"children": {
"worker_root": {
"total": 2289.1619137371067,
"count": 231897,
"is_parallel": true,
"self": 1074.9911516621341,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008956820000207699,
"count": 1,
"is_parallel": true,
"self": 0.00024607800003195734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006496039999888126,
"count": 2,
"is_parallel": true,
"self": 0.0006496039999888126
}
}
},
"UnityEnvironment.step": {
"total": 0.027793140999960997,
"count": 1,
"is_parallel": true,
"self": 0.00028793000001314795,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020489899998210603,
"count": 1,
"is_parallel": true,
"self": 0.00020489899998210603
},
"communicator.exchange": {
"total": 0.026619681999989098,
"count": 1,
"is_parallel": true,
"self": 0.026619681999989098
},
"steps_from_proto": {
"total": 0.0006806299999766452,
"count": 1,
"is_parallel": true,
"self": 0.0001945509999359274,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004860790000407178,
"count": 2,
"is_parallel": true,
"self": 0.0004860790000407178
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1214.1707620749726,
"count": 231896,
"is_parallel": true,
"self": 38.89158988599161,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.61989375506084,
"count": 231896,
"is_parallel": true,
"self": 79.61989375506084
},
"communicator.exchange": {
"total": 1009.6391073899206,
"count": 231896,
"is_parallel": true,
"self": 1009.6391073899206
},
"steps_from_proto": {
"total": 86.02017104399937,
"count": 231896,
"is_parallel": true,
"self": 30.29300937501904,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.72716166898033,
"count": 463792,
"is_parallel": true,
"self": 55.72716166898033
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 479.42618215595564,
"count": 231897,
"self": 6.18078977099259,
"children": {
"process_trajectory": {
"total": 141.20626934496403,
"count": 231897,
"self": 140.02261680696319,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1836525380008425,
"count": 10,
"self": 1.1836525380008425
}
}
},
"_update_policy": {
"total": 332.039123039999,
"count": 97,
"self": 271.71030130699353,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.3288217330055,
"count": 2910,
"self": 60.3288217330055
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.659997886046767e-07,
"count": 1,
"self": 9.659997886046767e-07
},
"TrainerController._save_models": {
"total": 0.09994817899996633,
"count": 1,
"self": 0.0017300999998042244,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0982180790001621,
"count": 1,
"self": 0.0982180790001621
}
}
}
}
}
}
}