ppo-Huggy / run_logs /timers.json
codeorange's picture
Huggy
eaa4fb5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.3982043266296387,
"min": 1.3982043266296387,
"max": 1.424781322479248,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69387.2890625,
"min": 68425.71875,
"max": 77219.9375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.79356060606061,
"min": 81.32078559738135,
"max": 392.8671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49523.0,
"min": 48824.0,
"max": 50287.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999999.0,
"min": 49932.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999999.0,
"min": 49932.0,
"max": 1999999.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4392049312591553,
"min": -0.15623775124549866,
"max": 2.485717535018921,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1287.900146484375,
"min": -19.842193603515625,
"max": 1460.202880859375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.788054948164658,
"min": 1.7231124564418643,
"max": 4.032298023612411,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2000.0930126309395,
"min": 218.83528196811676,
"max": 2304.5195472836494,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.788054948164658,
"min": 1.7231124564418643,
"max": 4.032298023612411,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2000.0930126309395,
"min": 218.83528196811676,
"max": 2304.5195472836494,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016734555774827537,
"min": 0.011088612838769525,
"max": 0.021202306619185644,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050203667324482615,
"min": 0.02217722567753905,
"max": 0.05742235219222493,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04905253131356504,
"min": 0.02516524695480863,
"max": 0.0603334479033947,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1471575939406951,
"min": 0.05033049390961726,
"max": 0.178757169470191,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.541248819616671e-06,
"min": 3.541248819616671e-06,
"max": 0.000295323076558975,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0623746458850013e-05,
"min": 1.0623746458850013e-05,
"max": 0.0008442703685765498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10118038333333335,
"min": 0.10118038333333335,
"max": 0.19844102500000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30354115000000004,
"min": 0.20752725,
"max": 0.58142345,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.89011283333334e-05,
"min": 6.89011283333334e-05,
"max": 0.0049222071475,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020670338500000023,
"min": 0.00020670338500000023,
"max": 0.014073030155,
"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": "1770967146",
"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": "1770969772"
},
"total": 2625.3387099609995,
"count": 1,
"self": 0.49408459899950685,
"children": {
"run_training.setup": {
"total": 0.027005272000224068,
"count": 1,
"self": 0.027005272000224068
},
"TrainerController.start_learning": {
"total": 2624.8176200899998,
"count": 1,
"self": 4.245922540976153,
"children": {
"TrainerController._reset_env": {
"total": 3.179004153000278,
"count": 1,
"self": 3.179004153000278
},
"TrainerController.advance": {
"total": 2617.2953451720246,
"count": 232316,
"self": 4.594745200183297,
"children": {
"env_step": {
"total": 2140.6693336227236,
"count": 232316,
"self": 1714.0173154688773,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.8058617371198,
"count": 232316,
"self": 16.11222126313396,
"children": {
"TorchPolicy.evaluate": {
"total": 407.69364047398585,
"count": 222956,
"self": 407.69364047398585
}
}
},
"workers": {
"total": 2.846156416726444,
"count": 232316,
"self": 0.0,
"children": {
"worker_root": {
"total": 2612.469577547908,
"count": 232316,
"is_parallel": true,
"self": 1222.3334945360239,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008559299999433279,
"count": 1,
"is_parallel": true,
"self": 0.00025735000053828117,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005985799994050467,
"count": 2,
"is_parallel": true,
"self": 0.0005985799994050467
}
}
},
"UnityEnvironment.step": {
"total": 0.030433825999807596,
"count": 1,
"is_parallel": true,
"self": 0.00032816499970067525,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00025497299975540955,
"count": 1,
"is_parallel": true,
"self": 0.00025497299975540955
},
"communicator.exchange": {
"total": 0.029161229000237654,
"count": 1,
"is_parallel": true,
"self": 0.029161229000237654
},
"steps_from_proto": {
"total": 0.0006894590001138567,
"count": 1,
"is_parallel": true,
"self": 0.00018493199968361296,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005045270004302438,
"count": 2,
"is_parallel": true,
"self": 0.0005045270004302438
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1390.1360830118842,
"count": 232315,
"is_parallel": true,
"self": 39.71609623905306,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.52070052087674,
"count": 232315,
"is_parallel": true,
"self": 86.52070052087674
},
"communicator.exchange": {
"total": 1171.2573930707977,
"count": 232315,
"is_parallel": true,
"self": 1171.2573930707977
},
"steps_from_proto": {
"total": 92.64189318115677,
"count": 232315,
"is_parallel": true,
"self": 33.47103721540634,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.170855965750434,
"count": 464630,
"is_parallel": true,
"self": 59.170855965750434
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 472.0312663491177,
"count": 232316,
"self": 6.541534163006418,
"children": {
"process_trajectory": {
"total": 157.43349703111107,
"count": 232316,
"self": 156.32747414511232,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1060228859987546,
"count": 10,
"self": 1.1060228859987546
}
}
},
"_update_policy": {
"total": 308.0562351550002,
"count": 97,
"self": 243.90479754401622,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.15143761098398,
"count": 2910,
"self": 64.15143761098398
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.709994290256873e-07,
"count": 1,
"self": 8.709994290256873e-07
},
"TrainerController._save_models": {
"total": 0.09734735299934982,
"count": 1,
"self": 0.0012129539991292404,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09613439900022058,
"count": 1,
"self": 0.09613439900022058
}
}
}
}
}
}
}