ppo-huggy / run_logs /timers.json
atk1432's picture
Huggy
cce28e0 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4127070903778076,
"min": 1.4127017259597778,
"max": 1.4313067197799683,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71037.9765625,
"min": 67989.984375,
"max": 78208.0,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 143.2622478386167,
"min": 94.18441064638783,
"max": 395.23622047244095,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49712.0,
"min": 48912.0,
"max": 50364.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999964.0,
"min": 49572.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999964.0,
"min": 49572.0,
"max": 1999964.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.112307548522949,
"min": 0.16610635817050934,
"max": 2.4104702472686768,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 730.8583984375,
"min": 20.929401397705078,
"max": 1237.4794921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.050792748356141,
"min": 1.85753637836093,
"max": 3.8934863744637904,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1055.5742909312248,
"min": 234.04958367347717,
"max": 2022.57940107584,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.050792748356141,
"min": 1.85753637836093,
"max": 3.8934863744637904,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1055.5742909312248,
"min": 234.04958367347717,
"max": 2022.57940107584,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017969254103081766,
"min": 0.014132622151252387,
"max": 0.020533810604744455,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03593850820616353,
"min": 0.028265244302504773,
"max": 0.061601431814233366,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.03489771007249753,
"min": 0.020353571170320113,
"max": 0.0578411835556229,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.06979542014499505,
"min": 0.040707142340640226,
"max": 0.15709503876666228,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.195973601375011e-06,
"min": 4.195973601375011e-06,
"max": 0.00029536447654517496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.391947202750021e-06,
"min": 8.391947202750021e-06,
"max": 0.00084395236868255,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10139862500000002,
"min": 0.10139862500000002,
"max": 0.19845482499999997,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20279725000000004,
"min": 0.20279725000000004,
"max": 0.58131745,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.979138750000014e-05,
"min": 7.979138750000014e-05,
"max": 0.004922895767500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00015958277500000028,
"min": 0.00015958277500000028,
"max": 0.014067740755,
"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": "1710665971",
"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=Huggy --no-graphics --force",
"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": "1710668469"
},
"total": 2497.4195532940003,
"count": 1,
"self": 0.4299764180004786,
"children": {
"run_training.setup": {
"total": 0.054951660000028824,
"count": 1,
"self": 0.054951660000028824
},
"TrainerController.start_learning": {
"total": 2496.934625216,
"count": 1,
"self": 4.588957677970484,
"children": {
"TrainerController._reset_env": {
"total": 2.5283002380000426,
"count": 1,
"self": 2.5283002380000426
},
"TrainerController.advance": {
"total": 2489.6971702920296,
"count": 230737,
"self": 4.997709866161131,
"children": {
"env_step": {
"total": 2017.7945062268518,
"count": 230737,
"self": 1667.792711625847,
"children": {
"SubprocessEnvManager._take_step": {
"total": 346.90393562696204,
"count": 230737,
"self": 18.600705501007212,
"children": {
"TorchPolicy.evaluate": {
"total": 328.3032301259548,
"count": 223110,
"self": 328.3032301259548
}
}
},
"workers": {
"total": 3.097858974042765,
"count": 230737,
"self": 0.0,
"children": {
"worker_root": {
"total": 2489.6904838550568,
"count": 230737,
"is_parallel": true,
"self": 1145.1791074060748,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009866949999945973,
"count": 1,
"is_parallel": true,
"self": 0.0002629539999929875,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007237410000016098,
"count": 2,
"is_parallel": true,
"self": 0.0007237410000016098
}
}
},
"UnityEnvironment.step": {
"total": 0.030043165999984467,
"count": 1,
"is_parallel": true,
"self": 0.0003786510000054477,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002151190000176939,
"count": 1,
"is_parallel": true,
"self": 0.0002151190000176939
},
"communicator.exchange": {
"total": 0.028664889999959087,
"count": 1,
"is_parallel": true,
"self": 0.028664889999959087
},
"steps_from_proto": {
"total": 0.0007845060000022386,
"count": 1,
"is_parallel": true,
"self": 0.0002029440000228533,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005815619999793853,
"count": 2,
"is_parallel": true,
"self": 0.0005815619999793853
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1344.511376448982,
"count": 230736,
"is_parallel": true,
"self": 40.45533834310845,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 88.01213148289986,
"count": 230736,
"is_parallel": true,
"self": 88.01213148289986
},
"communicator.exchange": {
"total": 1116.946323334977,
"count": 230736,
"is_parallel": true,
"self": 1116.946323334977
},
"steps_from_proto": {
"total": 99.09758328799677,
"count": 230736,
"is_parallel": true,
"self": 36.781086516024004,
"children": {
"_process_rank_one_or_two_observation": {
"total": 62.316496771972766,
"count": 461472,
"is_parallel": true,
"self": 62.316496771972766
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 466.90495419901646,
"count": 230737,
"self": 7.318305159992917,
"children": {
"process_trajectory": {
"total": 155.17905478702488,
"count": 230737,
"self": 153.61165637402524,
"children": {
"RLTrainer._checkpoint": {
"total": 1.567398412999637,
"count": 10,
"self": 1.567398412999637
}
}
},
"_update_policy": {
"total": 304.40759425199866,
"count": 96,
"self": 242.63854360999,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.769050642008665,
"count": 2880,
"self": 61.769050642008665
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.709998837730382e-07,
"count": 1,
"self": 8.709998837730382e-07
},
"TrainerController._save_models": {
"total": 0.12019613699976617,
"count": 1,
"self": 0.003102298999692721,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11709383800007345,
"count": 1,
"self": 0.11709383800007345
}
}
}
}
}
}
}