ppo-Huggy / run_logs /timers.json
expecto347's picture
Huggy~
77622b5 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.407172679901123,
"min": 1.407172679901123,
"max": 1.4283891916275024,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71573.0234375,
"min": 68486.484375,
"max": 77860.6875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 86.05729166666667,
"min": 86.05729166666667,
"max": 376.37593984962405,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49569.0,
"min": 48795.0,
"max": 50164.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999980.0,
"min": 49609.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999980.0,
"min": 49609.0,
"max": 1999980.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4056835174560547,
"min": 0.11077363044023514,
"max": 2.467216968536377,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1383.26806640625,
"min": 14.622118949890137,
"max": 1383.26806640625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.708046046650928,
"min": 1.6658480026279434,
"max": 3.9453983396180115,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2132.1264768242836,
"min": 219.89193634688854,
"max": 2132.1264768242836,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.708046046650928,
"min": 1.6658480026279434,
"max": 3.9453983396180115,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2132.1264768242836,
"min": 219.89193634688854,
"max": 2132.1264768242836,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017311811985402728,
"min": 0.01304427352103327,
"max": 0.019564575870875463,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.051935435956208184,
"min": 0.02608854704206654,
"max": 0.05601102247407349,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06158126381536325,
"min": 0.02177695818245411,
"max": 0.06158126381536325,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.18474379144608977,
"min": 0.04355391636490822,
"max": 0.18474379144608977,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.142048952683327e-06,
"min": 3.142048952683327e-06,
"max": 0.00029529375156875,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.426146858049981e-06,
"min": 9.426146858049981e-06,
"max": 0.0008437710187430001,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10104731666666665,
"min": 0.10104731666666665,
"max": 0.19843125000000003,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30314194999999994,
"min": 0.20723115000000006,
"max": 0.5812569999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.226110166666657e-05,
"min": 6.226110166666657e-05,
"max": 0.004921719375000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018678330499999972,
"min": 0.00018678330499999972,
"max": 0.014064724299999998,
"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": "1742175205",
"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": "1742177605"
},
"total": 2400.4871038849997,
"count": 1,
"self": 0.5363817020006536,
"children": {
"run_training.setup": {
"total": 0.01823912100007874,
"count": 1,
"self": 0.01823912100007874
},
"TrainerController.start_learning": {
"total": 2399.932483061999,
"count": 1,
"self": 4.9863603994253936,
"children": {
"TrainerController._reset_env": {
"total": 2.364165335000507,
"count": 1,
"self": 2.364165335000507
},
"TrainerController.advance": {
"total": 2392.427932665574,
"count": 231722,
"self": 4.49282964986196,
"children": {
"env_step": {
"total": 1988.341591154698,
"count": 231722,
"self": 1396.4392083718813,
"children": {
"SubprocessEnvManager._take_step": {
"total": 588.8495469425015,
"count": 231722,
"self": 16.386361480557753,
"children": {
"TorchPolicy.evaluate": {
"total": 572.4631854619438,
"count": 222979,
"self": 572.4631854619438
}
}
},
"workers": {
"total": 3.0528358403153106,
"count": 231722,
"self": 0.0,
"children": {
"worker_root": {
"total": 2389.7494701028445,
"count": 231722,
"is_parallel": true,
"self": 1242.9713760308023,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010299399982613977,
"count": 1,
"is_parallel": true,
"self": 0.00042471599954296835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006052239987184294,
"count": 2,
"is_parallel": true,
"self": 0.0006052239987184294
}
}
},
"UnityEnvironment.step": {
"total": 0.02714204900075856,
"count": 1,
"is_parallel": true,
"self": 0.00038881500222487375,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019770799917750992,
"count": 1,
"is_parallel": true,
"self": 0.00019770799917750992
},
"communicator.exchange": {
"total": 0.025943402000848437,
"count": 1,
"is_parallel": true,
"self": 0.025943402000848437
},
"steps_from_proto": {
"total": 0.0006121239985077409,
"count": 1,
"is_parallel": true,
"self": 0.00013550599760492332,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004766180009028176,
"count": 2,
"is_parallel": true,
"self": 0.0004766180009028176
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1146.7780940720422,
"count": 231721,
"is_parallel": true,
"self": 25.418898556612476,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 39.90782621071776,
"count": 231721,
"is_parallel": true,
"self": 39.90782621071776
},
"communicator.exchange": {
"total": 1028.8283493985327,
"count": 231721,
"is_parallel": true,
"self": 1028.8283493985327
},
"steps_from_proto": {
"total": 52.62301990617925,
"count": 231721,
"is_parallel": true,
"self": 18.22461472555915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 34.3984051806201,
"count": 463442,
"is_parallel": true,
"self": 34.3984051806201
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 399.5935118610141,
"count": 231722,
"self": 6.736412878160991,
"children": {
"process_trajectory": {
"total": 142.01552670384444,
"count": 231722,
"self": 140.8846829548438,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1308437490006327,
"count": 10,
"self": 1.1308437490006327
}
}
},
"_update_policy": {
"total": 250.8415722790087,
"count": 97,
"self": 192.84385698202277,
"children": {
"TorchPPOOptimizer.update": {
"total": 57.997715296985916,
"count": 2910,
"self": 57.997715296985916
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.999991117278114e-07,
"count": 1,
"self": 5.999991117278114e-07
},
"TrainerController._save_models": {
"total": 0.15402406199973484,
"count": 1,
"self": 0.0026358110008004587,
"children": {
"RLTrainer._checkpoint": {
"total": 0.15138825099893438,
"count": 1,
"self": 0.15138825099893438
}
}
}
}
}
}
}