ppo-Huggy / run_logs /timers.json
linqus's picture
Huggy
c8743bc
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.399540662765503,
"min": 1.399540662765503,
"max": 1.4247103929519653,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69329.046875,
"min": 68251.953125,
"max": 77276.703125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.26450511945393,
"min": 84.26450511945393,
"max": 392.0859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49379.0,
"min": 48948.0,
"max": 50187.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999994.0,
"min": 49884.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999994.0,
"min": 49884.0,
"max": 1999994.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4227685928344727,
"min": 0.0444682352244854,
"max": 2.46266770362854,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1419.742431640625,
"min": 5.647465705871582,
"max": 1419.742431640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7206866232608364,
"min": 1.8269301432324208,
"max": 3.923274675760621,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2180.32236123085,
"min": 232.02012819051743,
"max": 2247.9087837338448,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7206866232608364,
"min": 1.8269301432324208,
"max": 3.923274675760621,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2180.32236123085,
"min": 232.02012819051743,
"max": 2247.9087837338448,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017319164136359987,
"min": 0.01349325047012826,
"max": 0.02031045174711229,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05195749240907996,
"min": 0.02698650094025652,
"max": 0.0567280588511494,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05654399109383424,
"min": 0.023439966763059296,
"max": 0.061049483261174625,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16963197328150273,
"min": 0.04687993352611859,
"max": 0.18314844978352388,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.182298939266669e-06,
"min": 3.182298939266669e-06,
"max": 0.0002953625265458249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.546896817800006e-06,
"min": 9.546896817800006e-06,
"max": 0.00084426376857875,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106073333333336,
"min": 0.10106073333333336,
"max": 0.19845417500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30318220000000007,
"min": 0.20728294999999997,
"max": 0.5814212500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.293059333333337e-05,
"min": 6.293059333333337e-05,
"max": 0.0049228633325,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001887917800000001,
"min": 0.0001887917800000001,
"max": 0.014072920375,
"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": "1701552711",
"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=Huggy --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1701555146"
},
"total": 2434.1766559469997,
"count": 1,
"self": 0.44964729999992414,
"children": {
"run_training.setup": {
"total": 0.08654880299991419,
"count": 1,
"self": 0.08654880299991419
},
"TrainerController.start_learning": {
"total": 2433.640459844,
"count": 1,
"self": 4.612134379929103,
"children": {
"TrainerController._reset_env": {
"total": 4.06489035200002,
"count": 1,
"self": 4.06489035200002
},
"TrainerController.advance": {
"total": 2424.8612253530705,
"count": 232097,
"self": 4.646950439888769,
"children": {
"env_step": {
"total": 1920.378080892045,
"count": 232097,
"self": 1589.6963376371386,
"children": {
"SubprocessEnvManager._take_step": {
"total": 327.7743891319353,
"count": 232097,
"self": 16.36663328603504,
"children": {
"TorchPolicy.evaluate": {
"total": 311.4077558459003,
"count": 222849,
"self": 311.4077558459003
}
}
},
"workers": {
"total": 2.907354122971128,
"count": 232097,
"self": 0.0,
"children": {
"worker_root": {
"total": 2426.1657616468774,
"count": 232097,
"is_parallel": true,
"self": 1134.3938946750568,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009385099999690283,
"count": 1,
"is_parallel": true,
"self": 0.0002716979997785529,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006668120001904754,
"count": 2,
"is_parallel": true,
"self": 0.0006668120001904754
}
}
},
"UnityEnvironment.step": {
"total": 0.03014103499981502,
"count": 1,
"is_parallel": true,
"self": 0.00031224099961946195,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002153180000732391,
"count": 1,
"is_parallel": true,
"self": 0.0002153180000732391
},
"communicator.exchange": {
"total": 0.028917810000166355,
"count": 1,
"is_parallel": true,
"self": 0.028917810000166355
},
"steps_from_proto": {
"total": 0.0006956659999559633,
"count": 1,
"is_parallel": true,
"self": 0.00019059900000684138,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000505066999949122,
"count": 2,
"is_parallel": true,
"self": 0.000505066999949122
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1291.7718669718206,
"count": 232096,
"is_parallel": true,
"self": 39.83431317974737,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.70636357107878,
"count": 232096,
"is_parallel": true,
"self": 81.70636357107878
},
"communicator.exchange": {
"total": 1081.0887837669393,
"count": 232096,
"is_parallel": true,
"self": 1081.0887837669393
},
"steps_from_proto": {
"total": 89.14240645405516,
"count": 232096,
"is_parallel": true,
"self": 30.945769916189192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.19663653786597,
"count": 464192,
"is_parallel": true,
"self": 58.19663653786597
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 499.83619402113663,
"count": 232097,
"self": 7.048858779237662,
"children": {
"process_trajectory": {
"total": 156.55936613289919,
"count": 232097,
"self": 155.255272315899,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3040938170001937,
"count": 10,
"self": 1.3040938170001937
}
}
},
"_update_policy": {
"total": 336.2279691089998,
"count": 97,
"self": 272.25779753000074,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.97017157899904,
"count": 2910,
"self": 63.97017157899904
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.110000635497272e-07,
"count": 1,
"self": 8.110000635497272e-07
},
"TrainerController._save_models": {
"total": 0.10220894800022506,
"count": 1,
"self": 0.0016156590004356985,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10059328899978937,
"count": 1,
"self": 0.10059328899978937
}
}
}
}
}
}
}