ppo-Huggy / run_logs /timers.json
aardvarkjon's picture
Huggy
33d8c61 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4013633728027344,
"min": 1.4013633728027344,
"max": 1.428969383239746,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70093.390625,
"min": 68544.875,
"max": 75997.7109375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 80.78921568627452,
"min": 76.42700156985872,
"max": 395.1417322834646,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49443.0,
"min": 48684.0,
"max": 50183.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999977.0,
"min": 49615.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999977.0,
"min": 49615.0,
"max": 1999977.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4651596546173096,
"min": 0.15656235814094543,
"max": 2.4879066944122314,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1508.677734375,
"min": 19.726856231689453,
"max": 1544.5712890625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8733323029443327,
"min": 1.8592756557913999,
"max": 4.0494241365034815,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2370.4793694019318,
"min": 234.2687326297164,
"max": 2409.4822587370872,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8733323029443327,
"min": 1.8592756557913999,
"max": 4.0494241365034815,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2370.4793694019318,
"min": 234.2687326297164,
"max": 2409.4822587370872,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016874061444670792,
"min": 0.014582933190573992,
"max": 0.020269385924378488,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.050622184334012374,
"min": 0.029165866381147983,
"max": 0.05682876700496611,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.053389244526624684,
"min": 0.022098601050674915,
"max": 0.05710910639415184,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16016773357987404,
"min": 0.04419720210134983,
"max": 0.16043983275691667,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.625748791449991e-06,
"min": 3.625748791449991e-06,
"max": 0.0002952813015729,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0877246374349973e-05,
"min": 1.0877246374349973e-05,
"max": 0.0008438202187265998,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10120855,
"min": 0.10120855,
"max": 0.19842710000000008,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30362564999999997,
"min": 0.20755690000000004,
"max": 0.5812733999999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.030664499999986e-05,
"min": 7.030664499999986e-05,
"max": 0.00492151229,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002109199349999996,
"min": 0.0002109199349999996,
"max": 0.014065542660000003,
"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": "1733241122",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1733243648"
},
"total": 2526.295211565,
"count": 1,
"self": 0.4764317780004603,
"children": {
"run_training.setup": {
"total": 0.08603259400001662,
"count": 1,
"self": 0.08603259400001662
},
"TrainerController.start_learning": {
"total": 2525.732747193,
"count": 1,
"self": 4.605369220984812,
"children": {
"TrainerController._reset_env": {
"total": 5.767595455999981,
"count": 1,
"self": 5.767595455999981
},
"TrainerController.advance": {
"total": 2515.2482362260153,
"count": 233062,
"self": 4.6386964029602495,
"children": {
"env_step": {
"total": 1990.8600564569274,
"count": 233062,
"self": 1566.2466442650934,
"children": {
"SubprocessEnvManager._take_step": {
"total": 421.73400713897615,
"count": 233062,
"self": 15.739049987896806,
"children": {
"TorchPolicy.evaluate": {
"total": 405.99495715107935,
"count": 222971,
"self": 405.99495715107935
}
}
},
"workers": {
"total": 2.8794050528576918,
"count": 233062,
"self": 0.0,
"children": {
"worker_root": {
"total": 2518.2635448089077,
"count": 233062,
"is_parallel": true,
"self": 1242.664645119889,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000990270999977838,
"count": 1,
"is_parallel": true,
"self": 0.0002950560000272162,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006952149999506219,
"count": 2,
"is_parallel": true,
"self": 0.0006952149999506219
}
}
},
"UnityEnvironment.step": {
"total": 0.031159567999907267,
"count": 1,
"is_parallel": true,
"self": 0.0004062119998025082,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002036130000533376,
"count": 1,
"is_parallel": true,
"self": 0.0002036130000533376
},
"communicator.exchange": {
"total": 0.029725594000069577,
"count": 1,
"is_parallel": true,
"self": 0.029725594000069577
},
"steps_from_proto": {
"total": 0.0008241489999818441,
"count": 1,
"is_parallel": true,
"self": 0.00021193699990362802,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006122120000782161,
"count": 2,
"is_parallel": true,
"self": 0.0006122120000782161
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1275.5988996890187,
"count": 233061,
"is_parallel": true,
"self": 37.90127027015569,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.98636315194415,
"count": 233061,
"is_parallel": true,
"self": 83.98636315194415
},
"communicator.exchange": {
"total": 1062.9609513319924,
"count": 233061,
"is_parallel": true,
"self": 1062.9609513319924
},
"steps_from_proto": {
"total": 90.75031493492634,
"count": 233061,
"is_parallel": true,
"self": 33.940355904098396,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.80995903082794,
"count": 466122,
"is_parallel": true,
"self": 56.80995903082794
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 519.7494833661277,
"count": 233062,
"self": 6.645259449128844,
"children": {
"process_trajectory": {
"total": 178.11675414199817,
"count": 233062,
"self": 176.79685955199818,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3198945899999899,
"count": 10,
"self": 1.3198945899999899
}
}
},
"_update_policy": {
"total": 334.9874697750007,
"count": 97,
"self": 268.3943904019866,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.59307937301412,
"count": 2910,
"self": 66.59307937301412
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0439998732181266e-06,
"count": 1,
"self": 1.0439998732181266e-06
},
"TrainerController._save_models": {
"total": 0.1115452459998778,
"count": 1,
"self": 0.0028873709998151753,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10865787500006263,
"count": 1,
"self": 0.10865787500006263
}
}
}
}
}
}
}