ppo-Huggy / run_logs /timers.json
liyingjian's picture
Huggy
eda98a6
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4095321893692017,
"min": 1.4095321893692017,
"max": 1.4284428358078003,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71633.8359375,
"min": 69175.90625,
"max": 76906.515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 85.10172413793103,
"min": 74.9269406392694,
"max": 395.8412698412698,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49359.0,
"min": 48940.0,
"max": 50154.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999873.0,
"min": 49790.0,
"max": 1999873.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999873.0,
"min": 49790.0,
"max": 1999873.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4391539096832275,
"min": 0.033098891377449036,
"max": 2.4970977306365967,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1414.709228515625,
"min": 4.137361526489258,
"max": 1586.508544921875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.713681862169299,
"min": 1.7664331049919129,
"max": 4.0202425718307495,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2153.935480058193,
"min": 220.8041381239891,
"max": 2540.4591783881187,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.713681862169299,
"min": 1.7664331049919129,
"max": 4.0202425718307495,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2153.935480058193,
"min": 220.8041381239891,
"max": 2540.4591783881187,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018158235304710817,
"min": 0.013736612023138958,
"max": 0.0211427511756483,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05447470591413245,
"min": 0.02763763699331321,
"max": 0.05588993322259436,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.060672779546843636,
"min": 0.022461483068764207,
"max": 0.060672779546843636,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1820183386405309,
"min": 0.044922966137528414,
"max": 0.1820183386405309,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7095987634999996e-06,
"min": 3.7095987634999996e-06,
"max": 0.00029535232654922497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1128796290499998e-05,
"min": 1.1128796290499998e-05,
"max": 0.0008441314686228501,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10123650000000001,
"min": 0.10123650000000001,
"max": 0.198450775,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3037095,
"min": 0.2076034,
"max": 0.58137715,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.170135e-05,
"min": 7.170135e-05,
"max": 0.004922693672500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021510404999999997,
"min": 0.00021510404999999997,
"max": 0.014070719785000001,
"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": "1688689174",
"python_version": "3.10.12 (main, Jun 7 2023, 12:45:35) [GCC 9.4.0]",
"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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1688691723"
},
"total": 2548.954376957,
"count": 1,
"self": 0.6044841719999567,
"children": {
"run_training.setup": {
"total": 0.044321317000026283,
"count": 1,
"self": 0.044321317000026283
},
"TrainerController.start_learning": {
"total": 2548.305571468,
"count": 1,
"self": 4.652695912051513,
"children": {
"TrainerController._reset_env": {
"total": 4.133760741999936,
"count": 1,
"self": 4.133760741999936
},
"TrainerController.advance": {
"total": 2539.3887339859484,
"count": 232944,
"self": 4.843053086920918,
"children": {
"env_step": {
"total": 1978.0084035040363,
"count": 232944,
"self": 1666.101631434066,
"children": {
"SubprocessEnvManager._take_step": {
"total": 308.89752782799087,
"count": 232944,
"self": 17.69439496996074,
"children": {
"TorchPolicy.evaluate": {
"total": 291.20313285803013,
"count": 223042,
"self": 291.20313285803013
}
}
},
"workers": {
"total": 3.009244241979559,
"count": 232944,
"self": 0.0,
"children": {
"worker_root": {
"total": 2540.1342473850655,
"count": 232944,
"is_parallel": true,
"self": 1179.4458897960392,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009020009999858303,
"count": 1,
"is_parallel": true,
"self": 0.00021729099989897804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006847100000868522,
"count": 2,
"is_parallel": true,
"self": 0.0006847100000868522
}
}
},
"UnityEnvironment.step": {
"total": 0.03499477699995168,
"count": 1,
"is_parallel": true,
"self": 0.0003128869999500239,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002612170000020342,
"count": 1,
"is_parallel": true,
"self": 0.0002612170000020342
},
"communicator.exchange": {
"total": 0.03367212299997391,
"count": 1,
"is_parallel": true,
"self": 0.03367212299997391
},
"steps_from_proto": {
"total": 0.0007485500000257161,
"count": 1,
"is_parallel": true,
"self": 0.00021770700004708488,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005308429999786313,
"count": 2,
"is_parallel": true,
"self": 0.0005308429999786313
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1360.6883575890263,
"count": 232943,
"is_parallel": true,
"self": 40.39734034989351,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.62711982700387,
"count": 232943,
"is_parallel": true,
"self": 86.62711982700387
},
"communicator.exchange": {
"total": 1131.2771846640399,
"count": 232943,
"is_parallel": true,
"self": 1131.2771846640399
},
"steps_from_proto": {
"total": 102.38671274808917,
"count": 232943,
"is_parallel": true,
"self": 38.177332537413804,
"children": {
"_process_rank_one_or_two_observation": {
"total": 64.20938021067536,
"count": 465886,
"is_parallel": true,
"self": 64.20938021067536
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 556.5372773949911,
"count": 232944,
"self": 6.773026325993101,
"children": {
"process_trajectory": {
"total": 147.53704230999756,
"count": 232944,
"self": 146.06341960099735,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4736227090002103,
"count": 10,
"self": 1.4736227090002103
}
}
},
"_update_policy": {
"total": 402.2272087590004,
"count": 97,
"self": 340.64420320500835,
"children": {
"TorchPPOOptimizer.update": {
"total": 61.58300555399205,
"count": 2910,
"self": 61.58300555399205
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1130000530101825e-06,
"count": 1,
"self": 1.1130000530101825e-06
},
"TrainerController._save_models": {
"total": 0.13037971499988998,
"count": 1,
"self": 0.00245825599949967,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12792145900039031,
"count": 1,
"self": 0.12792145900039031
}
}
}
}
}
}
}