ppo-Huggy / run_logs /timers.json
Marc012DF's picture
Huggy
fe54736 verified
Raw
History Blame Contribute Delete
17.5 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4042223691940308,
"min": 1.4042223691940308,
"max": 1.4258053302764893,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70953.953125,
"min": 68247.890625,
"max": 76498.46875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 92.61121495327103,
"min": 80.63562091503267,
"max": 409.87704918032784,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49547.0,
"min": 48772.0,
"max": 50091.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999982.0,
"min": 49985.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999982.0,
"min": 49985.0,
"max": 1999982.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4285171031951904,
"min": 0.0623052716255188,
"max": 2.485422134399414,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1299.256591796875,
"min": 7.538938045501709,
"max": 1494.5654296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.744475634298592,
"min": 1.868563610413843,
"max": 3.9118885833052963,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2003.2944643497467,
"min": 226.096196860075,
"max": 2325.108390212059,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.744475634298592,
"min": 1.868563610413843,
"max": 3.9118885833052963,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2003.2944643497467,
"min": 226.096196860075,
"max": 2325.108390212059,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017812462534574375,
"min": 0.013745102242359685,
"max": 0.019572613546430754,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05343738760372313,
"min": 0.028646034157524508,
"max": 0.057366829794773366,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05309361277355088,
"min": 0.02190600677082936,
"max": 0.05901249146295919,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15928083832065265,
"min": 0.04381201354165872,
"max": 0.17703747438887757,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.321948892716671e-06,
"min": 3.321948892716671e-06,
"max": 0.00029523930158689997,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.965846678150013e-06,
"min": 9.965846678150013e-06,
"max": 0.0008437818187393999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10110728333333335,
"min": 0.10110728333333335,
"max": 0.19841310000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30332185000000006,
"min": 0.2073383,
"max": 0.5812606,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.52534383333334e-05,
"min": 6.52534383333334e-05,
"max": 0.00492081369,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001957603150000002,
"min": 0.0001957603150000002,
"max": 0.014064903940000002,
"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": "1775493453",
"python_version": "3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0]",
"command_line_arguments": "/home/eldoria/venvs/huggingface_drl/bonus_unit1venv/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=../trained-envs-executables/linux/Huggy/Huggy.x86_64 --run-id=Huggy2 --no-graphics --force",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1775495327"
},
"total": 1971.9713717900013,
"count": 1,
"self": 10.003137556001093,
"children": {
"run_training.setup": {
"total": 0.012449687999833259,
"count": 1,
"self": 0.012449687999833259
},
"TrainerController.start_learning": {
"total": 1961.9557845460004,
"count": 1,
"self": 3.49176193168023,
"children": {
"TrainerController._reset_env": {
"total": 1.9532684679998056,
"count": 1,
"self": 1.9532684679998056
},
"TrainerController.advance": {
"total": 1956.4430593983216,
"count": 232406,
"self": 3.06576018227679,
"children": {
"env_step": {
"total": 1661.5104041464147,
"count": 232406,
"self": 1103.3491942140226,
"children": {
"SubprocessEnvManager._take_step": {
"total": 555.7278481126323,
"count": 232406,
"self": 13.104464321799242,
"children": {
"TorchPolicy.evaluate": {
"total": 542.623383790833,
"count": 222948,
"self": 542.623383790833
}
}
},
"workers": {
"total": 2.433361819759739,
"count": 232406,
"self": 0.0,
"children": {
"worker_root": {
"total": 1954.7880434472445,
"count": 232406,
"is_parallel": true,
"self": 1034.0074596606337,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0004976600012014387,
"count": 1,
"is_parallel": true,
"self": 0.0001043780030158814,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0003932819981855573,
"count": 2,
"is_parallel": true,
"self": 0.0003932819981855573
}
}
},
"UnityEnvironment.step": {
"total": 0.01247074399907433,
"count": 1,
"is_parallel": true,
"self": 8.83209995663492e-05,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.679499999037944e-05,
"count": 1,
"is_parallel": true,
"self": 9.679499999037944e-05
},
"communicator.exchange": {
"total": 0.012053558999468805,
"count": 1,
"is_parallel": true,
"self": 0.012053558999468805
},
"steps_from_proto": {
"total": 0.00023206900004879571,
"count": 1,
"is_parallel": true,
"self": 5.2674999096780084e-05,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00017939400095201563,
"count": 2,
"is_parallel": true,
"self": 0.00017939400095201563
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 920.7805837866108,
"count": 232405,
"is_parallel": true,
"self": 16.818337064118168,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 28.00843801258452,
"count": 232405,
"is_parallel": true,
"self": 28.00843801258452
},
"communicator.exchange": {
"total": 838.3656275406211,
"count": 232405,
"is_parallel": true,
"self": 838.3656275406211
},
"steps_from_proto": {
"total": 37.588181169287054,
"count": 232405,
"is_parallel": true,
"self": 11.066214894510267,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.521966274776787,
"count": 464810,
"is_parallel": true,
"self": 26.521966274776787
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 291.8668950696301,
"count": 232406,
"self": 5.48973623553502,
"children": {
"process_trajectory": {
"total": 113.15858650309201,
"count": 232406,
"self": 112.18577169109267,
"children": {
"RLTrainer._checkpoint": {
"total": 0.972814811999342,
"count": 10,
"self": 0.972814811999342
}
}
},
"_update_policy": {
"total": 173.2185723310031,
"count": 97,
"self": 112.14664650708619,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.0719258239169,
"count": 2910,
"self": 61.0719258239169
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.589983291225508e-07,
"count": 1,
"self": 4.589983291225508e-07
},
"TrainerController._save_models": {
"total": 0.0676942890004284,
"count": 1,
"self": 0.0015387390012620017,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0661555499991664,
"count": 1,
"self": 0.0661555499991664
}
}
}
}
}
}
}