ppo-Huggy / run_logs /timers.json
mejdi86's picture
Huggy
475f98e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4060720205307007,
"min": 1.4060720205307007,
"max": 1.4302939176559448,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71024.9140625,
"min": 68287.2421875,
"max": 78930.28125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 76.76,
"min": 74.88467374810318,
"max": 422.1848739495798,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49894.0,
"min": 48736.0,
"max": 50240.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999808.0,
"min": 49477.0,
"max": 1999808.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999808.0,
"min": 49477.0,
"max": 1999808.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.432542324066162,
"min": 0.05809595063328743,
"max": 2.4776618480682373,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1581.152587890625,
"min": 7.378185749053955,
"max": 1615.991455078125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8044309391425206,
"min": 1.776684932586715,
"max": 3.9416111037532136,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2472.8801104426384,
"min": 225.6389864385128,
"max": 2491.1292608380318,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8044309391425206,
"min": 1.776684932586715,
"max": 3.9416111037532136,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2472.8801104426384,
"min": 225.6389864385128,
"max": 2491.1292608380318,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.013839342193940259,
"min": 0.013839342193940259,
"max": 0.021431330176710617,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04151802658182078,
"min": 0.029189165671899296,
"max": 0.06429399053013185,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05920774497919612,
"min": 0.02127311294898391,
"max": 0.06681431093149715,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17762323493758836,
"min": 0.04254622589796782,
"max": 0.20044293279449144,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5935988021666714e-06,
"min": 3.5935988021666714e-06,
"max": 0.00029538157653947496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0780796406500015e-05,
"min": 1.0780796406500015e-05,
"max": 0.00084394306868565,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10119783333333336,
"min": 0.10119783333333336,
"max": 0.19846052499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30359350000000007,
"min": 0.20752975,
"max": 0.58131435,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.977188333333342e-05,
"min": 6.977188333333342e-05,
"max": 0.0049231801975,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020931565000000026,
"min": 0.00020931565000000026,
"max": 0.014067586064999998,
"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": "1714897676",
"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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714900150"
},
"total": 2473.588455768,
"count": 1,
"self": 0.4391922289996728,
"children": {
"run_training.setup": {
"total": 0.05655154999999468,
"count": 1,
"self": 0.05655154999999468
},
"TrainerController.start_learning": {
"total": 2473.0927119890002,
"count": 1,
"self": 4.406355083029666,
"children": {
"TrainerController._reset_env": {
"total": 3.4496860030000107,
"count": 1,
"self": 3.4496860030000107
},
"TrainerController.advance": {
"total": 2465.1193581269704,
"count": 232378,
"self": 4.834944773958341,
"children": {
"env_step": {
"total": 1977.3796545660211,
"count": 232378,
"self": 1651.0864780750167,
"children": {
"SubprocessEnvManager._take_step": {
"total": 323.4002418959136,
"count": 232378,
"self": 16.586414513952263,
"children": {
"TorchPolicy.evaluate": {
"total": 306.81382738196135,
"count": 222940,
"self": 306.81382738196135
}
}
},
"workers": {
"total": 2.892934595090992,
"count": 232378,
"self": 0.0,
"children": {
"worker_root": {
"total": 2465.780669835034,
"count": 232378,
"is_parallel": true,
"self": 1128.6493062199875,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008974009999747068,
"count": 1,
"is_parallel": true,
"self": 0.0002269099999239188,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000670491000050788,
"count": 2,
"is_parallel": true,
"self": 0.000670491000050788
}
}
},
"UnityEnvironment.step": {
"total": 0.02999174900003254,
"count": 1,
"is_parallel": true,
"self": 0.0003754040001240355,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00024497099991549476,
"count": 1,
"is_parallel": true,
"self": 0.00024497099991549476
},
"communicator.exchange": {
"total": 0.02866232899998522,
"count": 1,
"is_parallel": true,
"self": 0.02866232899998522
},
"steps_from_proto": {
"total": 0.0007090450000077908,
"count": 1,
"is_parallel": true,
"self": 0.0001826989999926809,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005263460000151099,
"count": 2,
"is_parallel": true,
"self": 0.0005263460000151099
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1337.1313636150467,
"count": 232377,
"is_parallel": true,
"self": 40.045668231084164,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.84987843091005,
"count": 232377,
"is_parallel": true,
"self": 83.84987843091005
},
"communicator.exchange": {
"total": 1119.8229915809932,
"count": 232377,
"is_parallel": true,
"self": 1119.8229915809932
},
"steps_from_proto": {
"total": 93.41282537205916,
"count": 232377,
"is_parallel": true,
"self": 33.78821610009004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 59.62460927196912,
"count": 464754,
"is_parallel": true,
"self": 59.62460927196912
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 482.904758786991,
"count": 232378,
"self": 6.514443892980921,
"children": {
"process_trajectory": {
"total": 158.03708080900844,
"count": 232378,
"self": 156.67150656200954,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3655742469989036,
"count": 10,
"self": 1.3655742469989036
}
}
},
"_update_policy": {
"total": 318.35323408500165,
"count": 97,
"self": 256.38549259399304,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.96774149100861,
"count": 2910,
"self": 61.96774149100861
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.73000169324223e-07,
"count": 1,
"self": 9.73000169324223e-07
},
"TrainerController._save_models": {
"total": 0.11731180300012056,
"count": 1,
"self": 0.002043333000074199,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11526847000004636,
"count": 1,
"self": 0.11526847000004636
}
}
}
}
}
}
}