ppo-Huggy / run_logs /timers.json
MiVaCod's picture
Huggy
d97eb7e verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4052520990371704,
"min": 1.4052520990371704,
"max": 1.4295867681503296,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70345.515625,
"min": 69140.7890625,
"max": 76499.421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 82.01495016611295,
"min": 79.76575121163167,
"max": 390.65625,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49373.0,
"min": 48856.0,
"max": 50066.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999939.0,
"min": 49789.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999939.0,
"min": 49789.0,
"max": 1999939.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.469468116760254,
"min": 0.19185175001621246,
"max": 2.469468116760254,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1486.619873046875,
"min": 24.365171432495117,
"max": 1486.619873046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.827369615782139,
"min": 1.9827526095579928,
"max": 3.9871242495598618,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2304.0765087008476,
"min": 251.8095814138651,
"max": 2340.718613743782,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.827369615782139,
"min": 1.9827526095579928,
"max": 3.9871242495598618,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2304.0765087008476,
"min": 251.8095814138651,
"max": 2340.718613743782,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01824186414111561,
"min": 0.01267819567534995,
"max": 0.02032654629438184,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.054725592423346826,
"min": 0.0253563913506999,
"max": 0.05569546327072506,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.054823285796576075,
"min": 0.021940384929378828,
"max": 0.059390815409521264,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16446985738972822,
"min": 0.043880769858757655,
"max": 0.16446985738972822,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7801987399666747e-06,
"min": 3.7801987399666747e-06,
"max": 0.00029524245158585,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1340596219900024e-05,
"min": 1.1340596219900024e-05,
"max": 0.00084391546869485,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10126003333333333,
"min": 0.10126003333333333,
"max": 0.19841415,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037801,
"min": 0.2076482,
"max": 0.58130515,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.287566333333345e-05,
"min": 7.287566333333345e-05,
"max": 0.0049208660849999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021862699000000033,
"min": 0.00021862699000000033,
"max": 0.014067126984999997,
"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": "1715789473",
"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=Huggy2 --no-graphics",
"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": "1715792253"
},
"total": 2780.10999773,
"count": 1,
"self": 0.4954578799997762,
"children": {
"run_training.setup": {
"total": 0.08688834800000222,
"count": 1,
"self": 0.08688834800000222
},
"TrainerController.start_learning": {
"total": 2779.527651502,
"count": 1,
"self": 5.50921069502283,
"children": {
"TrainerController._reset_env": {
"total": 3.2728317060000336,
"count": 1,
"self": 3.2728317060000336
},
"TrainerController.advance": {
"total": 2770.6229077279772,
"count": 232622,
"self": 5.56192578387936,
"children": {
"env_step": {
"total": 2251.3777120600403,
"count": 232622,
"self": 1855.062293679021,
"children": {
"SubprocessEnvManager._take_step": {
"total": 392.39904886799377,
"count": 232622,
"self": 20.081760621023818,
"children": {
"TorchPolicy.evaluate": {
"total": 372.31728824696995,
"count": 222886,
"self": 372.31728824696995
}
}
},
"workers": {
"total": 3.916369513025529,
"count": 232622,
"self": 0.0,
"children": {
"worker_root": {
"total": 2770.895415045934,
"count": 232622,
"is_parallel": true,
"self": 1287.9969373269528,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010940760000721639,
"count": 1,
"is_parallel": true,
"self": 0.00032184100018639583,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000772234999885768,
"count": 2,
"is_parallel": true,
"self": 0.000772234999885768
}
}
},
"UnityEnvironment.step": {
"total": 0.04649386500000219,
"count": 1,
"is_parallel": true,
"self": 0.0004032680000136679,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00023012500003005698,
"count": 1,
"is_parallel": true,
"self": 0.00023012500003005698
},
"communicator.exchange": {
"total": 0.04483761999995295,
"count": 1,
"is_parallel": true,
"self": 0.04483761999995295
},
"steps_from_proto": {
"total": 0.0010228520000055141,
"count": 1,
"is_parallel": true,
"self": 0.00022543000000041502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007974220000050991,
"count": 2,
"is_parallel": true,
"self": 0.0007974220000050991
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1482.8984777189812,
"count": 232621,
"is_parallel": true,
"self": 43.71054941307625,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 93.5953187950239,
"count": 232621,
"is_parallel": true,
"self": 93.5953187950239
},
"communicator.exchange": {
"total": 1241.2852844509298,
"count": 232621,
"is_parallel": true,
"self": 1241.2852844509298
},
"steps_from_proto": {
"total": 104.30732505995115,
"count": 232621,
"is_parallel": true,
"self": 38.9088719680459,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.39845309190525,
"count": 465242,
"is_parallel": true,
"self": 65.39845309190525
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 513.6832698840576,
"count": 232622,
"self": 8.182939034961578,
"children": {
"process_trajectory": {
"total": 185.57885071509634,
"count": 232622,
"self": 184.02621862809633,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5526320870000063,
"count": 10,
"self": 1.5526320870000063
}
}
},
"_update_policy": {
"total": 319.9214801339997,
"count": 97,
"self": 255.54615105800292,
"children": {
"TorchPPOOptimizer.update": {
"total": 64.37532907599677,
"count": 2910,
"self": 64.37532907599677
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0839999049494509e-06,
"count": 1,
"self": 1.0839999049494509e-06
},
"TrainerController._save_models": {
"total": 0.12270028900002217,
"count": 1,
"self": 0.0022200039998097054,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12048028500021246,
"count": 1,
"self": 0.12048028500021246
}
}
}
}
}
}
}