ppo-Huggy / run_logs /timers.json
Peilin00's picture
Huggy
5177f42 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401172399520874,
"min": 1.401172399520874,
"max": 1.4277735948562622,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69764.375,
"min": 68663.53125,
"max": 77758.6015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.6436170212766,
"min": 79.41318327974277,
"max": 397.244094488189,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49431.0,
"min": 48998.0,
"max": 50450.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999951.0,
"min": 49952.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999951.0,
"min": 49952.0,
"max": 1999951.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4061949253082275,
"min": 0.0004385209467727691,
"max": 2.4808974266052246,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1357.093994140625,
"min": 0.055253639817237854,
"max": 1498.954345703125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.709530366756392,
"min": 1.806620002029434,
"max": 3.9510300948373525,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2092.175126850605,
"min": 227.6341202557087,
"max": 2347.6474482119083,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.709530366756392,
"min": 1.806620002029434,
"max": 3.9510300948373525,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2092.175126850605,
"min": 227.6341202557087,
"max": 2347.6474482119083,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017460182260482626,
"min": 0.01250800937511182,
"max": 0.020934542467390807,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05238054678144788,
"min": 0.02501601875022364,
"max": 0.05849762100794275,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05611225304504236,
"min": 0.02367926388978958,
"max": 0.06426581734170517,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16833675913512708,
"min": 0.04735852777957916,
"max": 0.187985547631979,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.407798864100003e-06,
"min": 3.407798864100003e-06,
"max": 0.000295340176553275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.022339659230001e-05,
"min": 1.022339659230001e-05,
"max": 0.0008440980186339999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10113590000000001,
"min": 0.10113590000000001,
"max": 0.19844672499999996,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30340770000000006,
"min": 0.20740920000000007,
"max": 0.581366,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.668141000000005e-05,
"min": 6.668141000000005e-05,
"max": 0.0049224915775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020004423000000016,
"min": 0.00020004423000000016,
"max": 0.0140701634,
"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": "1740170987",
"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=Huggy --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": "1740173553"
},
"total": 2566.1039358410003,
"count": 1,
"self": 0.4398524900002485,
"children": {
"run_training.setup": {
"total": 0.022211039000012534,
"count": 1,
"self": 0.022211039000012534
},
"TrainerController.start_learning": {
"total": 2565.641872312,
"count": 1,
"self": 4.643631743074366,
"children": {
"TrainerController._reset_env": {
"total": 2.890059113999996,
"count": 1,
"self": 2.890059113999996
},
"TrainerController.advance": {
"total": 2557.9935873759255,
"count": 232565,
"self": 5.193489915894588,
"children": {
"env_step": {
"total": 2055.421216800013,
"count": 232565,
"self": 1609.2090895939355,
"children": {
"SubprocessEnvManager._take_step": {
"total": 443.43275950800887,
"count": 232565,
"self": 16.349128017975147,
"children": {
"TorchPolicy.evaluate": {
"total": 427.0836314900337,
"count": 222924,
"self": 427.0836314900337
}
}
},
"workers": {
"total": 2.779367698068711,
"count": 232565,
"self": 0.0,
"children": {
"worker_root": {
"total": 2557.9992076340454,
"count": 232565,
"is_parallel": true,
"self": 1248.7687726370714,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010922269999582568,
"count": 1,
"is_parallel": true,
"self": 0.00026859999996986517,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0008236269999883916,
"count": 2,
"is_parallel": true,
"self": 0.0008236269999883916
}
}
},
"UnityEnvironment.step": {
"total": 0.02961225699999659,
"count": 1,
"is_parallel": true,
"self": 0.000324737000028108,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001843480000047748,
"count": 1,
"is_parallel": true,
"self": 0.0001843480000047748
},
"communicator.exchange": {
"total": 0.02841041699997504,
"count": 1,
"is_parallel": true,
"self": 0.02841041699997504
},
"steps_from_proto": {
"total": 0.0006927549999886651,
"count": 1,
"is_parallel": true,
"self": 0.00020134200002530633,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004914129999633587,
"count": 2,
"is_parallel": true,
"self": 0.0004914129999633587
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1309.230434996974,
"count": 232564,
"is_parallel": true,
"self": 38.69070613810254,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.56131416905816,
"count": 232564,
"is_parallel": true,
"self": 85.56131416905816
},
"communicator.exchange": {
"total": 1094.4357848049149,
"count": 232564,
"is_parallel": true,
"self": 1094.4357848049149
},
"steps_from_proto": {
"total": 90.54262988489825,
"count": 232564,
"is_parallel": true,
"self": 33.559209225851475,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.98342065904677,
"count": 465128,
"is_parallel": true,
"self": 56.98342065904677
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 497.37888066001796,
"count": 232565,
"self": 7.1138736209500735,
"children": {
"process_trajectory": {
"total": 172.54829731106804,
"count": 232565,
"self": 171.1703103460685,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3779869649995362,
"count": 10,
"self": 1.3779869649995362
}
}
},
"_update_policy": {
"total": 317.71670972799984,
"count": 97,
"self": 251.20859658000154,
"children": {
"TorchPPOOptimizer.update": {
"total": 66.5081131479983,
"count": 2910,
"self": 66.5081131479983
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.629999683762435e-07,
"count": 1,
"self": 8.629999683762435e-07
},
"TrainerController._save_models": {
"total": 0.11459321600023031,
"count": 1,
"self": 0.001819826000428293,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11277338999980202,
"count": 1,
"self": 0.11277338999980202
}
}
}
}
}
}
}