ppo-Huggy / run_logs /timers.json
Elahe96's picture
Huggy
7f59c19 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4114700555801392,
"min": 1.4114540815353394,
"max": 1.429111361503601,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69512.078125,
"min": 68507.859375,
"max": 76390.1328125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.31226765799256,
"min": 83.98639455782313,
"max": 414.3801652892562,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49664.0,
"min": 48977.0,
"max": 50140.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999484.0,
"min": 49835.0,
"max": 1999484.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999484.0,
"min": 49835.0,
"max": 1999484.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.482562303543091,
"min": 0.21041446924209595,
"max": 2.5316994190216064,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1335.6185302734375,
"min": 25.249736785888672,
"max": 1443.462890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9199762832941176,
"min": 1.80555879175663,
"max": 4.020716315959917,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2108.9472404122353,
"min": 216.6670550107956,
"max": 2308.096722304821,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9199762832941176,
"min": 1.80555879175663,
"max": 4.020716315959917,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2108.9472404122353,
"min": 216.6670550107956,
"max": 2308.096722304821,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01461775971046235,
"min": 0.013971010050348317,
"max": 0.021935085039391802,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04385327913138705,
"min": 0.027942020100696633,
"max": 0.058274719334440304,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05658766076796584,
"min": 0.020326070580631496,
"max": 0.0656058101190461,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16976298230389752,
"min": 0.04065214116126299,
"max": 0.1968174303571383,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4425988524999933e-06,
"min": 3.4425988524999933e-06,
"max": 0.00029528197657267504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.032779655749998e-05,
"min": 1.032779655749998e-05,
"max": 0.0008440614186461999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1011475,
"min": 0.1011475,
"max": 0.198427325,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3034425,
"min": 0.20744749999999995,
"max": 0.5813538000000003,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.726024999999991e-05,
"min": 6.726024999999991e-05,
"max": 0.0049215235175,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020178074999999972,
"min": 0.00020178074999999972,
"max": 0.01406955462,
"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": "1718907133",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1718909818"
},
"total": 2685.747376208,
"count": 1,
"self": 0.5465127230004327,
"children": {
"run_training.setup": {
"total": 0.08506591999957891,
"count": 1,
"self": 0.08506591999957891
},
"TrainerController.start_learning": {
"total": 2685.115797565,
"count": 1,
"self": 4.817405498991775,
"children": {
"TrainerController._reset_env": {
"total": 3.48254976599992,
"count": 1,
"self": 3.48254976599992
},
"TrainerController.advance": {
"total": 2676.6902694530086,
"count": 232307,
"self": 5.125346985820215,
"children": {
"env_step": {
"total": 2119.0904324111634,
"count": 232307,
"self": 1746.3417911665492,
"children": {
"SubprocessEnvManager._take_step": {
"total": 369.43381689889657,
"count": 232307,
"self": 19.016627733983114,
"children": {
"TorchPolicy.evaluate": {
"total": 350.41718916491345,
"count": 222898,
"self": 350.41718916491345
}
}
},
"workers": {
"total": 3.314824345717625,
"count": 232307,
"self": 0.0,
"children": {
"worker_root": {
"total": 2677.507930161909,
"count": 232307,
"is_parallel": true,
"self": 1274.1756131620677,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012343210000835825,
"count": 1,
"is_parallel": true,
"self": 0.00035254500016890233,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008817759999146801,
"count": 2,
"is_parallel": true,
"self": 0.0008817759999146801
}
}
},
"UnityEnvironment.step": {
"total": 0.03277288499975839,
"count": 1,
"is_parallel": true,
"self": 0.0003808450001088204,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023082799998519477,
"count": 1,
"is_parallel": true,
"self": 0.00023082799998519477
},
"communicator.exchange": {
"total": 0.0313785549997192,
"count": 1,
"is_parallel": true,
"self": 0.0313785549997192
},
"steps_from_proto": {
"total": 0.0007826569999451749,
"count": 1,
"is_parallel": true,
"self": 0.00020712599962280365,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005755310003223713,
"count": 2,
"is_parallel": true,
"self": 0.0005755310003223713
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1403.3323169998412,
"count": 232306,
"is_parallel": true,
"self": 42.52086242257883,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 92.70385021817219,
"count": 232306,
"is_parallel": true,
"self": 92.70385021817219
},
"communicator.exchange": {
"total": 1169.2391192430682,
"count": 232306,
"is_parallel": true,
"self": 1169.2391192430682
},
"steps_from_proto": {
"total": 98.86848511602193,
"count": 232306,
"is_parallel": true,
"self": 37.79918114426755,
"children": {
"_process_rank_one_or_two_observation": {
"total": 61.06930397175438,
"count": 464612,
"is_parallel": true,
"self": 61.06930397175438
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 552.4744900560249,
"count": 232307,
"self": 7.174239310923895,
"children": {
"process_trajectory": {
"total": 169.0128048790989,
"count": 232307,
"self": 167.45859466609863,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5542102130002604,
"count": 10,
"self": 1.5542102130002604
}
}
},
"_update_policy": {
"total": 376.28744586600214,
"count": 97,
"self": 308.56578964202754,
"children": {
"TorchPPOOptimizer.update": {
"total": 67.7216562239746,
"count": 2910,
"self": 67.7216562239746
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2459995559765957e-06,
"count": 1,
"self": 1.2459995559765957e-06
},
"TrainerController._save_models": {
"total": 0.12557160100004694,
"count": 1,
"self": 0.0020352269993964,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12353637400065054,
"count": 1,
"self": 0.12353637400065054
}
}
}
}
}
}
}