ppo-Huggy / run_logs /timers.json
zapsdcn's picture
Huggy
1e792eb verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4052469730377197,
"min": 1.4052469730377197,
"max": 1.4278013706207275,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69646.8515625,
"min": 69305.3359375,
"max": 76937.953125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.96246246246247,
"min": 71.99124087591241,
"max": 395.59055118110234,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49259.0,
"min": 49042.0,
"max": 50240.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999922.0,
"min": 49617.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999922.0,
"min": 49617.0,
"max": 1999922.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.5206573009490967,
"min": 0.125038281083107,
"max": 2.5508434772491455,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1678.7576904296875,
"min": 15.754823684692383,
"max": 1733.7135009765625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.904171407222748,
"min": 1.867247939582855,
"max": 4.034779006623999,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2600.17815721035,
"min": 235.27324038743973,
"max": 2644.397199988365,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.904171407222748,
"min": 1.867247939582855,
"max": 4.034779006623999,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2600.17815721035,
"min": 235.27324038743973,
"max": 2644.397199988365,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014228655516570952,
"min": 0.01370367104601529,
"max": 0.02069418469230489,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04268596654971286,
"min": 0.027820918700793604,
"max": 0.060883988170341276,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06294727097782825,
"min": 0.022237246762961148,
"max": 0.0672078151255846,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18884181293348473,
"min": 0.044474493525922296,
"max": 0.2016234453767538,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.5205488265166646e-06,
"min": 3.5205488265166646e-06,
"max": 0.0002953136265621249,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0561646479549993e-05,
"min": 1.0561646479549993e-05,
"max": 0.0008439727686757499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10117348333333336,
"min": 0.10117348333333336,
"max": 0.19843787500000007,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30352045000000005,
"min": 0.20750700000000002,
"max": 0.58132425,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.855681833333327e-05,
"min": 6.855681833333327e-05,
"max": 0.004922049962499999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002056704549999998,
"min": 0.0002056704549999998,
"max": 0.014068080075,
"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": "1743745448",
"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=Huggy3 --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": "1743747972"
},
"total": 2523.799048063,
"count": 1,
"self": 0.7008603659996879,
"children": {
"run_training.setup": {
"total": 0.02053732699999955,
"count": 1,
"self": 0.02053732699999955
},
"TrainerController.start_learning": {
"total": 2523.0776503700004,
"count": 1,
"self": 4.62713893800219,
"children": {
"TrainerController._reset_env": {
"total": 1.9835222620000081,
"count": 1,
"self": 1.9835222620000081
},
"TrainerController.advance": {
"total": 2516.2913865209985,
"count": 233302,
"self": 4.650672285962173,
"children": {
"env_step": {
"total": 2020.1439900780315,
"count": 233302,
"self": 1584.1893726130388,
"children": {
"SubprocessEnvManager._take_step": {
"total": 433.1809264660316,
"count": 233302,
"self": 16.38790477195971,
"children": {
"TorchPolicy.evaluate": {
"total": 416.7930216940719,
"count": 222907,
"self": 416.7930216940719
}
}
},
"workers": {
"total": 2.773690998961058,
"count": 233302,
"self": 0.0,
"children": {
"worker_root": {
"total": 2515.2329396559167,
"count": 233302,
"is_parallel": true,
"self": 1221.6156520109957,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008918319999793312,
"count": 1,
"is_parallel": true,
"self": 0.0002813060000335099,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006105259999458212,
"count": 2,
"is_parallel": true,
"self": 0.0006105259999458212
}
}
},
"UnityEnvironment.step": {
"total": 0.030157002000009925,
"count": 1,
"is_parallel": true,
"self": 0.0002544430000170905,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019072000003461653,
"count": 1,
"is_parallel": true,
"self": 0.00019072000003461653
},
"communicator.exchange": {
"total": 0.028874309999991965,
"count": 1,
"is_parallel": true,
"self": 0.028874309999991965
},
"steps_from_proto": {
"total": 0.0008375289999662527,
"count": 1,
"is_parallel": true,
"self": 0.00021541899997146174,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000622109999994791,
"count": 2,
"is_parallel": true,
"self": 0.000622109999994791
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1293.617287644921,
"count": 233301,
"is_parallel": true,
"self": 37.40207787587656,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 84.51090794397703,
"count": 233301,
"is_parallel": true,
"self": 84.51090794397703
},
"communicator.exchange": {
"total": 1082.583679287986,
"count": 233301,
"is_parallel": true,
"self": 1082.583679287986
},
"steps_from_proto": {
"total": 89.12062253708126,
"count": 233301,
"is_parallel": true,
"self": 33.261698291214316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 55.858924245866945,
"count": 466602,
"is_parallel": true,
"self": 55.858924245866945
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.4967241570047,
"count": 233302,
"self": 7.23477589588822,
"children": {
"process_trajectory": {
"total": 176.32033194611859,
"count": 233302,
"self": 175.0023692691185,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3179626770000823,
"count": 10,
"self": 1.3179626770000823
}
}
},
"_update_policy": {
"total": 307.9416163149979,
"count": 97,
"self": 243.04963765599524,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.89197865900263,
"count": 2910,
"self": 64.89197865900263
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.451999651180813e-06,
"count": 1,
"self": 1.451999651180813e-06
},
"TrainerController._save_models": {
"total": 0.17560119700010546,
"count": 1,
"self": 0.003008849000252667,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1725923479998528,
"count": 1,
"self": 0.1725923479998528
}
}
}
}
}
}
}