ppo-Huggy / run_logs /timers.json
Pie33000's picture
Huggy
a210dec verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4007941484451294,
"min": 1.4007941484451294,
"max": 1.4259872436523438,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68531.0546875,
"min": 68531.0546875,
"max": 76433.1484375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 81.78311258278146,
"min": 77.4662480376766,
"max": 390.1860465116279,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49397.0,
"min": 48870.0,
"max": 50334.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999976.0,
"min": 49823.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999976.0,
"min": 49823.0,
"max": 1999976.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4542219638824463,
"min": 0.05890761315822601,
"max": 2.4838080406188965,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1482.35009765625,
"min": 7.54017448425293,
"max": 1549.938232421875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.7620429888071603,
"min": 1.8600714555941522,
"max": 3.986011703289672,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2272.273965239525,
"min": 238.08914631605148,
"max": 2442.5266039967537,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.7620429888071603,
"min": 1.8600714555941522,
"max": 3.986011703289672,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2272.273965239525,
"min": 238.08914631605148,
"max": 2442.5266039967537,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01980323544056672,
"min": 0.013463927384085157,
"max": 0.02013952041694817,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05940970632170016,
"min": 0.026927854768170313,
"max": 0.05940970632170016,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0575653214007616,
"min": 0.022604822056988876,
"max": 0.05899305529892444,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1726959642022848,
"min": 0.04520964411397775,
"max": 0.1726959642022848,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4800988399999928e-06,
"min": 3.4800988399999928e-06,
"max": 0.00029534085155305,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0440296519999979e-05,
"min": 1.0440296519999979e-05,
"max": 0.00084381256872915,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115999999999999,
"min": 0.10115999999999999,
"max": 0.19844695000000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30347999999999997,
"min": 0.20749944999999997,
"max": 0.5812708500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.788399999999992e-05,
"min": 6.788399999999992e-05,
"max": 0.004922502805000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020365199999999978,
"min": 0.00020365199999999978,
"max": 0.014065415415000001,
"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": "1738788781",
"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": "1738791419"
},
"total": 2637.204547237,
"count": 1,
"self": 0.43868215899965435,
"children": {
"run_training.setup": {
"total": 0.023188201000039044,
"count": 1,
"self": 0.023188201000039044
},
"TrainerController.start_learning": {
"total": 2636.742676877,
"count": 1,
"self": 5.035821389164994,
"children": {
"TrainerController._reset_env": {
"total": 2.998996365000039,
"count": 1,
"self": 2.998996365000039
},
"TrainerController.advance": {
"total": 2628.5895672338347,
"count": 232690,
"self": 5.108408342770417,
"children": {
"env_step": {
"total": 2120.167391043982,
"count": 232690,
"self": 1660.4315546228704,
"children": {
"SubprocessEnvManager._take_step": {
"total": 456.6105662010816,
"count": 232690,
"self": 17.106625535135095,
"children": {
"TorchPolicy.evaluate": {
"total": 439.5039406659465,
"count": 222856,
"self": 439.5039406659465
}
}
},
"workers": {
"total": 3.1252702200300746,
"count": 232690,
"self": 0.0,
"children": {
"worker_root": {
"total": 2628.395175506971,
"count": 232690,
"is_parallel": true,
"self": 1278.590855849877,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010853629999019176,
"count": 1,
"is_parallel": true,
"self": 0.00040122299981248943,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006841400000894282,
"count": 2,
"is_parallel": true,
"self": 0.0006841400000894282
}
}
},
"UnityEnvironment.step": {
"total": 0.0314783339999849,
"count": 1,
"is_parallel": true,
"self": 0.0003769870000951414,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019477099999676284,
"count": 1,
"is_parallel": true,
"self": 0.00019477099999676284
},
"communicator.exchange": {
"total": 0.03019466699993245,
"count": 1,
"is_parallel": true,
"self": 0.03019466699993245
},
"steps_from_proto": {
"total": 0.0007119089999605421,
"count": 1,
"is_parallel": true,
"self": 0.00018633499996667524,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005255739999938669,
"count": 2,
"is_parallel": true,
"self": 0.0005255739999938669
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1349.804319657094,
"count": 232689,
"is_parallel": true,
"self": 38.36400090410484,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.16709124502393,
"count": 232689,
"is_parallel": true,
"self": 85.16709124502393
},
"communicator.exchange": {
"total": 1133.1984633869974,
"count": 232689,
"is_parallel": true,
"self": 1133.1984633869974
},
"steps_from_proto": {
"total": 93.07476412096776,
"count": 232689,
"is_parallel": true,
"self": 34.36390386589471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.710860255073044,
"count": 465378,
"is_parallel": true,
"self": 58.710860255073044
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 503.3137678470823,
"count": 232690,
"self": 7.667932002058706,
"children": {
"process_trajectory": {
"total": 184.60670004002657,
"count": 232690,
"self": 183.22049550602662,
"children": {
"RLTrainer._checkpoint": {
"total": 1.386204533999944,
"count": 10,
"self": 1.386204533999944
}
}
},
"_update_policy": {
"total": 311.03913580499704,
"count": 97,
"self": 245.00005697899394,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.0390788260031,
"count": 2910,
"self": 66.0390788260031
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.240002327715047e-07,
"count": 1,
"self": 9.240002327715047e-07
},
"TrainerController._save_models": {
"total": 0.11829096500014202,
"count": 1,
"self": 0.0018939070000669744,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11639705800007505,
"count": 1,
"self": 0.11639705800007505
}
}
}
}
}
}
}