ppo-adihuggy / run_logs /timers.json
isnt-adi's picture
Huggy
faee0bc verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.40577232837677,
"min": 1.40577232837677,
"max": 1.428716778755188,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71612.8515625,
"min": 69023.21875,
"max": 78182.8984375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.06319702602231,
"min": 82.6964586846543,
"max": 390.859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49530.0,
"min": 48869.0,
"max": 50076.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999520.0,
"min": 49938.0,
"max": 1999520.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999520.0,
"min": 49938.0,
"max": 1999520.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.440289258956909,
"min": 0.12388387322425842,
"max": 2.440289258956909,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1312.8756103515625,
"min": 15.733251571655273,
"max": 1429.4049072265625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8031531522486732,
"min": 1.808811567430421,
"max": 3.931063721556928,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2046.0963959097862,
"min": 229.71906906366348,
"max": 2251.047212600708,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8031531522486732,
"min": 1.808811567430421,
"max": 3.931063721556928,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2046.0963959097862,
"min": 229.71906906366348,
"max": 2251.047212600708,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01707362222696247,
"min": 0.012987295805942267,
"max": 0.02086354073495992,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05122086668088741,
"min": 0.025974591611884534,
"max": 0.05945184592079992,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05197152814103497,
"min": 0.02082048471396168,
"max": 0.057214884025355184,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1559145844231049,
"min": 0.04164096942792336,
"max": 0.164567427833875,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5263988245666593e-06,
"min": 3.5263988245666593e-06,
"max": 0.0002953022265659251,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0579196473699978e-05,
"min": 1.0579196473699978e-05,
"max": 0.00084399166866945,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117543333333334,
"min": 0.10117543333333334,
"max": 0.19843407500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3035263,
"min": 0.20751609999999998,
"max": 0.5813305500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.865412333333322e-05,
"min": 6.865412333333322e-05,
"max": 0.004921860342500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020596236999999968,
"min": 0.00020596236999999968,
"max": 0.014068394445,
"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": "1740326390",
"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": "1740328847"
},
"total": 2456.976205643,
"count": 1,
"self": 0.4402499360003276,
"children": {
"run_training.setup": {
"total": 0.023555806999979723,
"count": 1,
"self": 0.023555806999979723
},
"TrainerController.start_learning": {
"total": 2456.5123998999998,
"count": 1,
"self": 4.4279778020290905,
"children": {
"TrainerController._reset_env": {
"total": 3.8341819240000063,
"count": 1,
"self": 3.8341819240000063
},
"TrainerController.advance": {
"total": 2448.1301686039706,
"count": 231877,
"self": 4.70480889295095,
"children": {
"env_step": {
"total": 1967.0754895319435,
"count": 231877,
"self": 1541.23496524981,
"children": {
"SubprocessEnvManager._take_step": {
"total": 423.21576896895783,
"count": 231877,
"self": 15.80531216701911,
"children": {
"TorchPolicy.evaluate": {
"total": 407.4104568019387,
"count": 223008,
"self": 407.4104568019387
}
}
},
"workers": {
"total": 2.624755313175683,
"count": 231877,
"self": 0.0,
"children": {
"worker_root": {
"total": 2449.1776285159995,
"count": 231877,
"is_parallel": true,
"self": 1188.2203288329242,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0012399830000049405,
"count": 1,
"is_parallel": true,
"self": 0.00027938000005178765,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0009606029999531529,
"count": 2,
"is_parallel": true,
"self": 0.0009606029999531529
}
}
},
"UnityEnvironment.step": {
"total": 0.029617401999985304,
"count": 1,
"is_parallel": true,
"self": 0.00032447999996065846,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020117799999752606,
"count": 1,
"is_parallel": true,
"self": 0.00020117799999752606
},
"communicator.exchange": {
"total": 0.0283557460000452,
"count": 1,
"is_parallel": true,
"self": 0.0283557460000452
},
"steps_from_proto": {
"total": 0.0007359979999819188,
"count": 1,
"is_parallel": true,
"self": 0.00021425499994620623,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005217430000357126,
"count": 2,
"is_parallel": true,
"self": 0.0005217430000357126
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1260.9572996830752,
"count": 231876,
"is_parallel": true,
"self": 37.875290780947125,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 80.74550512305842,
"count": 231876,
"is_parallel": true,
"self": 80.74550512305842
},
"communicator.exchange": {
"total": 1055.221088803003,
"count": 231876,
"is_parallel": true,
"self": 1055.221088803003
},
"steps_from_proto": {
"total": 87.11541497606652,
"count": 231876,
"is_parallel": true,
"self": 30.68091435397406,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.43450062209246,
"count": 463752,
"is_parallel": true,
"self": 56.43450062209246
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 476.3498701790761,
"count": 231877,
"self": 6.550261545047022,
"children": {
"process_trajectory": {
"total": 160.56440669802873,
"count": 231877,
"self": 159.13588345002938,
"children": {
"RLTrainer._checkpoint": {
"total": 1.428523247999351,
"count": 10,
"self": 1.428523247999351
}
}
},
"_update_policy": {
"total": 309.23520193600035,
"count": 97,
"self": 244.6824020819871,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.55279985401324,
"count": 2910,
"self": 64.55279985401324
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.790002539171837e-07,
"count": 1,
"self": 8.790002539171837e-07
},
"TrainerController._save_models": {
"total": 0.12007069099990986,
"count": 1,
"self": 0.0027273330001662544,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1173433579997436,
"count": 1,
"self": 0.1173433579997436
}
}
}
}
}
}
}