ppo-Huggy / run_logs /timers.json
Ram贸n
Huggy
37874d0
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4067292213439941,
"min": 1.4067292213439941,
"max": 1.4315265417099,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69716.09375,
"min": 67924.5234375,
"max": 78146.796875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 93.64583333333333,
"min": 89.04830053667263,
"max": 388.87692307692305,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49445.0,
"min": 48778.0,
"max": 50554.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999962.0,
"min": 49991.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999962.0,
"min": 49991.0,
"max": 1999962.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.386913776397705,
"min": 0.06870283931493759,
"max": 2.4165074825286865,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1260.29052734375,
"min": 8.862666130065918,
"max": 1327.2811279296875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.688115638878309,
"min": 1.7923889562141064,
"max": 3.9593226188811186,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1947.3250573277473,
"min": 231.21817535161972,
"max": 2118.2376011013985,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.688115638878309,
"min": 1.7923889562141064,
"max": 3.9593226188811186,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1947.3250573277473,
"min": 231.21817535161972,
"max": 2118.2376011013985,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016181046917659436,
"min": 0.013279130003744892,
"max": 0.0200403155235108,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04854314075297831,
"min": 0.026558260007489783,
"max": 0.05666846116801025,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05262461474372281,
"min": 0.021325153888513644,
"max": 0.061239102172354856,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.15787384423116843,
"min": 0.04265030777702729,
"max": 0.17635625240703423,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4687488437833286e-06,
"min": 3.4687488437833286e-06,
"max": 0.00029533785155404994,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0406246531349986e-05,
"min": 1.0406246531349986e-05,
"max": 0.0008441512686162499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115621666666669,
"min": 0.10115621666666669,
"max": 0.1984459500000001,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30346865000000006,
"min": 0.20745794999999995,
"max": 0.5813837499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.769521166666658e-05,
"min": 6.769521166666658e-05,
"max": 0.004922452905000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00020308563499999975,
"min": 0.00020308563499999975,
"max": 0.014071049124999995,
"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": "1670922244",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1670924479"
},
"total": 2234.696121872,
"count": 1,
"self": 0.3959138239993081,
"children": {
"run_training.setup": {
"total": 0.11063907100003689,
"count": 1,
"self": 0.11063907100003689
},
"TrainerController.start_learning": {
"total": 2234.1895689770004,
"count": 1,
"self": 3.967868735967386,
"children": {
"TrainerController._reset_env": {
"total": 9.753776173000006,
"count": 1,
"self": 9.753776173000006
},
"TrainerController.advance": {
"total": 2220.3578585690334,
"count": 231871,
"self": 4.057221518025472,
"children": {
"env_step": {
"total": 1754.8489934550698,
"count": 231871,
"self": 1471.919080080202,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.25904562588744,
"count": 231871,
"self": 14.27345569091068,
"children": {
"TorchPolicy.evaluate": {
"total": 265.98558993497676,
"count": 222996,
"self": 66.0035937529334,
"children": {
"TorchPolicy.sample_actions": {
"total": 199.98199618204336,
"count": 222996,
"self": 199.98199618204336
}
}
}
}
},
"workers": {
"total": 2.6708677489802426,
"count": 231871,
"self": 0.0,
"children": {
"worker_root": {
"total": 2226.2253410699764,
"count": 231871,
"is_parallel": true,
"self": 1018.9714414739503,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002052133999995931,
"count": 1,
"is_parallel": true,
"self": 0.0003410190000181501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017111149999777808,
"count": 2,
"is_parallel": true,
"self": 0.0017111149999777808
}
}
},
"UnityEnvironment.step": {
"total": 0.028579201000013654,
"count": 1,
"is_parallel": true,
"self": 0.0002585579999845322,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001899750000120548,
"count": 1,
"is_parallel": true,
"self": 0.0001899750000120548
},
"communicator.exchange": {
"total": 0.02740048499998693,
"count": 1,
"is_parallel": true,
"self": 0.02740048499998693
},
"steps_from_proto": {
"total": 0.0007301830000301379,
"count": 1,
"is_parallel": true,
"self": 0.00027516700004071026,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00045501599998942766,
"count": 2,
"is_parallel": true,
"self": 0.00045501599998942766
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1207.253899596026,
"count": 231870,
"is_parallel": true,
"self": 34.55132771197532,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.8573572070652,
"count": 231870,
"is_parallel": true,
"self": 79.8573572070652
},
"communicator.exchange": {
"total": 998.2233033679531,
"count": 231870,
"is_parallel": true,
"self": 998.2233033679531
},
"steps_from_proto": {
"total": 94.62191130903238,
"count": 231870,
"is_parallel": true,
"self": 40.652503740001066,
"children": {
"_process_rank_one_or_two_observation": {
"total": 53.96940756903132,
"count": 463740,
"is_parallel": true,
"self": 53.96940756903132
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 461.451643595938,
"count": 231871,
"self": 6.235236317938984,
"children": {
"process_trajectory": {
"total": 148.38928921399867,
"count": 231871,
"self": 147.91643199599872,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4728572179999446,
"count": 4,
"self": 0.4728572179999446
}
}
},
"_update_policy": {
"total": 306.82711806400033,
"count": 97,
"self": 253.22185288100212,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.60526518299821,
"count": 2910,
"self": 53.60526518299821
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.689997568784747e-07,
"count": 1,
"self": 9.689997568784747e-07
},
"TrainerController._save_models": {
"total": 0.11006452999981775,
"count": 1,
"self": 0.0019351800001459196,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10812934999967183,
"count": 1,
"self": 0.10812934999967183
}
}
}
}
}
}
}