ppo-Huggy / run_logs /timers.json
Enzogbs's picture
Huggy
bf65a28 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406181812286377,
"min": 1.40617835521698,
"max": 1.430260419845581,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70626.890625,
"min": 68978.2578125,
"max": 76023.8359375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.56849315068493,
"min": 83.95925297113752,
"max": 419.92436974789916,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49388.0,
"min": 49017.0,
"max": 50283.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999905.0,
"min": 49761.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999905.0,
"min": 49761.0,
"max": 1999905.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.402846336364746,
"min": 0.119190514087677,
"max": 2.4554080963134766,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1403.26220703125,
"min": 14.064480781555176,
"max": 1412.664306640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.809841454539397,
"min": 1.752357323290938,
"max": 3.9654420774331767,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2224.947409451008,
"min": 206.7781641483307,
"max": 2243.1758006215096,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.809841454539397,
"min": 1.752357323290938,
"max": 3.9654420774331767,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2224.947409451008,
"min": 206.7781641483307,
"max": 2243.1758006215096,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01760452258216295,
"min": 0.013315559323321699,
"max": 0.019511137306002034,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05281356774648885,
"min": 0.026631118646643397,
"max": 0.05312774869040973,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.058629369901286234,
"min": 0.02181278569623828,
"max": 0.05984081356889672,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1758881097038587,
"min": 0.04362557139247656,
"max": 0.17952244070669016,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.81569872813333e-06,
"min": 3.81569872813333e-06,
"max": 0.000295313476562175,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.144709618439999e-05,
"min": 1.144709618439999e-05,
"max": 0.0008441997186000998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1012718666666667,
"min": 0.1012718666666667,
"max": 0.198437825,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038156000000001,
"min": 0.20766875000000007,
"max": 0.5813999000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.346614666666662e-05,
"min": 7.346614666666662e-05,
"max": 0.004922047467499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022039843999999985,
"min": 0.00022039843999999985,
"max": 0.014071855009999999,
"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": "1750002385",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1750004696"
},
"total": 2310.246458532,
"count": 1,
"self": 0.4470170390000021,
"children": {
"run_training.setup": {
"total": 0.03416618899996138,
"count": 1,
"self": 0.03416618899996138
},
"TrainerController.start_learning": {
"total": 2309.765275304,
"count": 1,
"self": 3.9120312661298158,
"children": {
"TrainerController._reset_env": {
"total": 3.616619982000202,
"count": 1,
"self": 3.616619982000202
},
"TrainerController.advance": {
"total": 2302.1232346538704,
"count": 231709,
"self": 4.217711675094961,
"children": {
"env_step": {
"total": 1840.302315753907,
"count": 231709,
"self": 1454.5539952269517,
"children": {
"SubprocessEnvManager._take_step": {
"total": 383.24697737594533,
"count": 231709,
"self": 14.239203968987567,
"children": {
"TorchPolicy.evaluate": {
"total": 369.00777340695777,
"count": 222848,
"self": 369.00777340695777
}
}
},
"workers": {
"total": 2.5013431510099053,
"count": 231709,
"self": 0.0,
"children": {
"worker_root": {
"total": 2302.6606386469916,
"count": 231709,
"is_parallel": true,
"self": 1117.7621944411153,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008592550000230403,
"count": 1,
"is_parallel": true,
"self": 0.0002459160000398697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006133389999831707,
"count": 2,
"is_parallel": true,
"self": 0.0006133389999831707
}
}
},
"UnityEnvironment.step": {
"total": 0.02871509600004174,
"count": 1,
"is_parallel": true,
"self": 0.00031790200000614277,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019155199993292626,
"count": 1,
"is_parallel": true,
"self": 0.00019155199993292626
},
"communicator.exchange": {
"total": 0.027532811000128277,
"count": 1,
"is_parallel": true,
"self": 0.027532811000128277
},
"steps_from_proto": {
"total": 0.0006728309999743942,
"count": 1,
"is_parallel": true,
"self": 0.0001914229999329109,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004814080000414833,
"count": 2,
"is_parallel": true,
"self": 0.0004814080000414833
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1184.8984442058763,
"count": 231708,
"is_parallel": true,
"self": 36.34303143896136,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 77.6907112149604,
"count": 231708,
"is_parallel": true,
"self": 77.6907112149604
},
"communicator.exchange": {
"total": 986.0610967860803,
"count": 231708,
"is_parallel": true,
"self": 986.0610967860803
},
"steps_from_proto": {
"total": 84.8036047658743,
"count": 231708,
"is_parallel": true,
"self": 30.120418180737943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.683186585136355,
"count": 463416,
"is_parallel": true,
"self": 54.683186585136355
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 457.6032072248688,
"count": 231709,
"self": 5.896666943780929,
"children": {
"process_trajectory": {
"total": 148.49740538209085,
"count": 231709,
"self": 147.35649572909074,
"children": {
"RLTrainer._checkpoint": {
"total": 1.140909653000108,
"count": 10,
"self": 1.140909653000108
}
}
},
"_update_policy": {
"total": 303.20913489899704,
"count": 97,
"self": 241.1580874679978,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.05104743099923,
"count": 2910,
"self": 62.05104743099923
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.889993867138401e-07,
"count": 1,
"self": 7.889993867138401e-07
},
"TrainerController._save_models": {
"total": 0.1133886130000974,
"count": 1,
"self": 0.001542816999972274,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11184579600012512,
"count": 1,
"self": 0.11184579600012512
}
}
}
}
}
}
}