ppo-Huggy / run_logs /timers.json
maxhykw's picture
Huggy
b42f1b0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4068695306777954,
"min": 1.4068695306777954,
"max": 1.42767333984375,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71616.6953125,
"min": 69233.59375,
"max": 76911.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.4555052790347,
"min": 72.30938416422288,
"max": 419.6890756302521,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49364.0,
"min": 49270.0,
"max": 50211.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999925.0,
"min": 49383.0,
"max": 1999925.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999925.0,
"min": 49383.0,
"max": 1999925.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.535909652709961,
"min": 0.12668967247009277,
"max": 2.535909652709961,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1681.30810546875,
"min": 14.949380874633789,
"max": 1694.3944091796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.964214810059261,
"min": 2.1198274154784316,
"max": 4.008672973721018,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2628.27441906929,
"min": 250.13963502645493,
"max": 2630.785528898239,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.964214810059261,
"min": 2.1198274154784316,
"max": 4.008672973721018,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2628.27441906929,
"min": 250.13963502645493,
"max": 2630.785528898239,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016066611229325647,
"min": 0.012417566352653212,
"max": 0.019886367357745863,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04819983368797694,
"min": 0.027801295225314486,
"max": 0.05888378143426962,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05881600495841768,
"min": 0.021210515995820363,
"max": 0.06208231747150421,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17644801487525302,
"min": 0.042421031991640726,
"max": 0.1799617967257897,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5209988263666603e-06,
"min": 3.5209988263666603e-06,
"max": 0.00029531070156309995,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0562996479099981e-05,
"min": 1.0562996479099981e-05,
"max": 0.0008439672186775998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117363333333335,
"min": 0.10117363333333335,
"max": 0.1984369,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30352090000000004,
"min": 0.20750615,
"max": 0.5813224000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.856430333333323e-05,
"min": 6.856430333333323e-05,
"max": 0.00492200131,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020569290999999967,
"min": 0.00020569290999999967,
"max": 0.014067987759999998,
"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": "1741976413",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1741980234"
},
"total": 3820.8615846979997,
"count": 1,
"self": 0.5387873829995442,
"children": {
"run_training.setup": {
"total": 0.04108789400004298,
"count": 1,
"self": 0.04108789400004298
},
"TrainerController.start_learning": {
"total": 3820.281709421,
"count": 1,
"self": 6.95855131998951,
"children": {
"TrainerController._reset_env": {
"total": 3.9850621260000025,
"count": 1,
"self": 3.9850621260000025
},
"TrainerController.advance": {
"total": 3809.2042399290103,
"count": 233288,
"self": 6.848783773973992,
"children": {
"env_step": {
"total": 2400.2129463230567,
"count": 233288,
"self": 2007.8640329451655,
"children": {
"SubprocessEnvManager._take_step": {
"total": 388.1035814098675,
"count": 233288,
"self": 22.449434508956756,
"children": {
"TorchPolicy.evaluate": {
"total": 365.65414690091075,
"count": 222991,
"self": 365.65414690091075
}
}
},
"workers": {
"total": 4.24533196802372,
"count": 233288,
"self": 0.0,
"children": {
"worker_root": {
"total": 3809.6604664109486,
"count": 233288,
"is_parallel": true,
"self": 2195.5462776659583,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012463809999871955,
"count": 1,
"is_parallel": true,
"self": 0.00045813400004135474,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007882469999458408,
"count": 2,
"is_parallel": true,
"self": 0.0007882469999458408
}
}
},
"UnityEnvironment.step": {
"total": 0.05623224700002538,
"count": 1,
"is_parallel": true,
"self": 0.00037644100007128145,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023787399993580038,
"count": 1,
"is_parallel": true,
"self": 0.00023787399993580038
},
"communicator.exchange": {
"total": 0.05464871599997423,
"count": 1,
"is_parallel": true,
"self": 0.05464871599997423
},
"steps_from_proto": {
"total": 0.0009692160000440708,
"count": 1,
"is_parallel": true,
"self": 0.00022243500006879913,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007467809999752717,
"count": 2,
"is_parallel": true,
"self": 0.0007467809999752717
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1614.1141887449903,
"count": 233287,
"is_parallel": true,
"self": 49.83702523002694,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 98.52704791898077,
"count": 233287,
"is_parallel": true,
"self": 98.52704791898077
},
"communicator.exchange": {
"total": 1347.7374323498607,
"count": 233287,
"is_parallel": true,
"self": 1347.7374323498607
},
"steps_from_proto": {
"total": 118.01268324612181,
"count": 233287,
"is_parallel": true,
"self": 39.58462363727301,
"children": {
"_process_rank_one_or_two_observation": {
"total": 78.4280596088488,
"count": 466574,
"is_parallel": true,
"self": 78.4280596088488
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1402.1425098319796,
"count": 233288,
"self": 10.209479783904271,
"children": {
"process_trajectory": {
"total": 236.92085632707335,
"count": 233288,
"self": 235.56230232607436,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3585540009989927,
"count": 10,
"self": 1.3585540009989927
}
}
},
"_update_policy": {
"total": 1155.012173721002,
"count": 97,
"self": 298.46981518000916,
"children": {
"TorchPPOOptimizer.update": {
"total": 856.5423585409928,
"count": 2910,
"self": 856.5423585409928
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1729998732334934e-06,
"count": 1,
"self": 1.1729998732334934e-06
},
"TrainerController._save_models": {
"total": 0.13385487300001842,
"count": 1,
"self": 0.008702317999450315,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1251525550005681,
"count": 1,
"self": 0.1251525550005681
}
}
}
}
}
}
}