ppo-Huggy / run_logs /timers.json
MathgeniusTB's picture
Huggy
e2153a2 verified
Raw
History Blame Contribute Delete
17.4 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.406853437423706,
"min": 1.406853437423706,
"max": 1.4291778802871704,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70214.6484375,
"min": 69099.40625,
"max": 76542.046875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.93497363796133,
"min": 79.74151857835218,
"max": 396.3253968253968,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49466.0,
"min": 48970.0,
"max": 50291.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999350.0,
"min": 49649.0,
"max": 1999350.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999350.0,
"min": 49649.0,
"max": 1999350.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5006966590881348,
"min": 0.08694195747375488,
"max": 2.5006966590881348,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1422.8963623046875,
"min": 10.867744445800781,
"max": 1484.337890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8805591389667797,
"min": 1.8659011368751526,
"max": 3.9650310072691544,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2208.038150072098,
"min": 233.23764210939407,
"max": 2296.9371811151505,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8805591389667797,
"min": 1.8659011368751526,
"max": 3.9650310072691544,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2208.038150072098,
"min": 233.23764210939407,
"max": 2296.9371811151505,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.019437984030810183,
"min": 0.013707299428157663,
"max": 0.019437984030810183,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05831395209243055,
"min": 0.027414598856315326,
"max": 0.05831395209243055,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.057414521359735064,
"min": 0.0216558947848777,
"max": 0.06185183218783802,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17224356407920519,
"min": 0.0433117895697554,
"max": 0.18555549656351406,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.672298775933337e-06,
"min": 3.672298775933337e-06,
"max": 0.00029535465154845,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1016896327800011e-05,
"min": 1.1016896327800011e-05,
"max": 0.0008438869687043499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122406666666667,
"min": 0.10122406666666667,
"max": 0.19845155000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3036722,
"min": 0.20767109999999994,
"max": 0.5812956499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.10809266666667e-05,
"min": 7.10809266666667e-05,
"max": 0.004922732345,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021324278000000012,
"min": 0.00021324278000000012,
"max": 0.014066652935,
"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": "1769134992",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769137735"
},
"total": 2742.780689619,
"count": 1,
"self": 0.8121796319996974,
"children": {
"run_training.setup": {
"total": 0.02675041199995576,
"count": 1,
"self": 0.02675041199995576
},
"TrainerController.start_learning": {
"total": 2741.941759575,
"count": 1,
"self": 4.565670415113345,
"children": {
"TrainerController._reset_env": {
"total": 3.833648117999928,
"count": 1,
"self": 3.833648117999928
},
"TrainerController.advance": {
"total": 2733.3905354318867,
"count": 232818,
"self": 4.658927047947145,
"children": {
"env_step": {
"total": 2234.07217244897,
"count": 232818,
"self": 1803.706343782153,
"children": {
"SubprocessEnvManager._take_step": {
"total": 427.4227622109504,
"count": 232818,
"self": 16.68278854790674,
"children": {
"TorchPolicy.evaluate": {
"total": 410.73997366304366,
"count": 223004,
"self": 410.73997366304366
}
}
},
"workers": {
"total": 2.9430664558665285,
"count": 232818,
"self": 0.0,
"children": {
"worker_root": {
"total": 2728.7086302709977,
"count": 232818,
"is_parallel": true,
"self": 1269.7058421999661,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009091260001241608,
"count": 1,
"is_parallel": true,
"self": 0.0002703039999687462,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006388220001554146,
"count": 2,
"is_parallel": true,
"self": 0.0006388220001554146
}
}
},
"UnityEnvironment.step": {
"total": 0.03238742000007733,
"count": 1,
"is_parallel": true,
"self": 0.0003520739999203215,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019338600009177753,
"count": 1,
"is_parallel": true,
"self": 0.00019338600009177753
},
"communicator.exchange": {
"total": 0.030996724000033282,
"count": 1,
"is_parallel": true,
"self": 0.030996724000033282
},
"steps_from_proto": {
"total": 0.0008452360000319459,
"count": 1,
"is_parallel": true,
"self": 0.00020938299985573394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006358530001762119,
"count": 2,
"is_parallel": true,
"self": 0.0006358530001762119
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1459.0027880710315,
"count": 232817,
"is_parallel": true,
"self": 41.35728598905666,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 91.09073815407555,
"count": 232817,
"is_parallel": true,
"self": 91.09073815407555
},
"communicator.exchange": {
"total": 1228.4967007099692,
"count": 232817,
"is_parallel": true,
"self": 1228.4967007099692
},
"steps_from_proto": {
"total": 98.05806321793011,
"count": 232817,
"is_parallel": true,
"self": 35.549061439880234,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.50900177804988,
"count": 465634,
"is_parallel": true,
"self": 62.50900177804988
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.65943593496945,
"count": 232818,
"self": 6.79425538692567,
"children": {
"process_trajectory": {
"total": 167.5153205210438,
"count": 232818,
"self": 166.23729416104425,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2780263599995578,
"count": 10,
"self": 1.2780263599995578
}
}
},
"_update_policy": {
"total": 320.349860027,
"count": 97,
"self": 255.36538933300926,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.98447069399072,
"count": 2910,
"self": 64.98447069399072
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.4950001059332862e-06,
"count": 1,
"self": 1.4950001059332862e-06
},
"TrainerController._save_models": {
"total": 0.15190411499997936,
"count": 1,
"self": 0.0019360840001354518,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1499680309998439,
"count": 1,
"self": 0.1499680309998439
}
}
}
}
}
}
}