ppo-Huggy / run_logs /timers.json
igpaub's picture
Huggy
e9d7cb1
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.313913106918335,
"min": 1.313913106918335,
"max": 1.317245602607727,
"count": 10
},
"Huggy.Policy.Entropy.sum": {
"value": 130664.71875,
"min": 129024.421875,
"max": 134149.609375,
"count": 10
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 87.24889673433363,
"min": 65.08658294778586,
"max": 87.24889673433363,
"count": 10
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 98853.0,
"min": 98171.0,
"max": 99332.0,
"count": 10
},
"Huggy.Step.mean": {
"value": 4999924.0,
"min": 4099982.0,
"max": 4999924.0,
"count": 10
},
"Huggy.Step.sum": {
"value": 4999924.0,
"min": 4099982.0,
"max": 4999924.0,
"count": 10
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4324426651000977,
"min": 2.4324426651000977,
"max": 2.5505118370056152,
"count": 10
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 2755.95751953125,
"min": 2755.95751953125,
"max": 3833.5390625,
"count": 10
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8079658567852817,
"min": 3.8079658567852817,
"max": 4.05654823921314,
"count": 10
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 4314.425315737724,
"min": 4314.425315737724,
"max": 6065.738024711609,
"count": 10
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8079658567852817,
"min": 3.8079658567852817,
"max": 4.05654823921314,
"count": 10
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 4314.425315737724,
"min": 4314.425315737724,
"max": 6065.738024711609,
"count": 10
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.014701851868497517,
"min": 0.014126381898283094,
"max": 0.018514142019800298,
"count": 10
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.07350925934248759,
"min": 0.056505527593132376,
"max": 0.09103437434144629,
"count": 10
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.046128600587447485,
"min": 0.04368286759903033,
"max": 0.061055387215067945,
"count": 10
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.23064300293723744,
"min": 0.184973868355155,
"max": 0.2889091414709886,
"count": 10
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2159309280559994e-06,
"min": 3.2159309280559994e-06,
"max": 5.6923386025565e-05,
"count": 10
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.6079654640279996e-05,
"min": 1.6079654640279996e-05,
"max": 0.00025691765436091995,
"count": 10
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10107194400000001,
"min": 0.10107194400000001,
"max": 0.11897443500000002,
"count": 10
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.5053597200000001,
"min": 0.41994962,
"max": 0.58563908,
"count": 10
},
"Huggy.Policy.Beta.mean": {
"value": 6.349000560000001e-05,
"min": 6.349000560000001e-05,
"max": 0.0009568243065000003,
"count": 10
},
"Huggy.Policy.Beta.sum": {
"value": 0.0003174500280000001,
"min": 0.0003174500280000001,
"max": 0.004323390092,
"count": 10
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1698755973",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=Huggy --no-graphics --resume",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.1.0+cu118",
"numpy_version": "1.23.5",
"end_time_seconds": "1698757333"
},
"total": 1359.5616869530004,
"count": 1,
"self": 0.8612719400007336,
"children": {
"run_training.setup": {
"total": 0.044629289000113204,
"count": 1,
"self": 0.044629289000113204
},
"TrainerController.start_learning": {
"total": 1358.6557857239995,
"count": 1,
"self": 2.4366720811076448,
"children": {
"TrainerController._reset_env": {
"total": 4.315022652999687,
"count": 1,
"self": 4.315022652999687
},
"TrainerController.advance": {
"total": 1350.7282377618922,
"count": 117824,
"self": 2.5804658236475007,
"children": {
"env_step": {
"total": 1042.6086795740512,
"count": 117824,
"self": 842.6668168675587,
"children": {
"SubprocessEnvManager._take_step": {
"total": 198.37702805137997,
"count": 117824,
"self": 8.648324341295847,
"children": {
"TorchPolicy.evaluate": {
"total": 189.72870371008412,
"count": 111736,
"self": 189.72870371008412
}
}
},
"workers": {
"total": 1.5648346551124632,
"count": 117824,
"self": 0.0,
"children": {
"worker_root": {
"total": 1348.1955729422607,
"count": 117824,
"is_parallel": true,
"self": 665.3405499071905,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008575070005463203,
"count": 1,
"is_parallel": true,
"self": 0.0002671370002644835,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005903700002818368,
"count": 2,
"is_parallel": true,
"self": 0.0005903700002818368
}
}
},
"UnityEnvironment.step": {
"total": 0.03037778299949423,
"count": 1,
"is_parallel": true,
"self": 0.0002948659994217451,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020318899987614714,
"count": 1,
"is_parallel": true,
"self": 0.00020318899987614714
},
"communicator.exchange": {
"total": 0.029165697999815166,
"count": 1,
"is_parallel": true,
"self": 0.029165697999815166
},
"steps_from_proto": {
"total": 0.0007140300003811717,
"count": 1,
"is_parallel": true,
"self": 0.00020293600027798675,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000511094000103185,
"count": 2,
"is_parallel": true,
"self": 0.000511094000103185
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 682.8550230350702,
"count": 117823,
"is_parallel": true,
"self": 20.995316780616122,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 45.75232028135997,
"count": 117823,
"is_parallel": true,
"self": 45.75232028135997
},
"communicator.exchange": {
"total": 568.0529631481322,
"count": 117823,
"is_parallel": true,
"self": 568.0529631481322
},
"steps_from_proto": {
"total": 48.054422824961875,
"count": 117823,
"is_parallel": true,
"self": 18.1666580222236,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.887764802738275,
"count": 235646,
"is_parallel": true,
"self": 29.887764802738275
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 305.5390923641935,
"count": 117824,
"self": 3.3789918170332385,
"children": {
"process_trajectory": {
"total": 112.73238724916064,
"count": 117824,
"self": 94.71496339116038,
"children": {
"RLTrainer._checkpoint": {
"total": 18.017423858000257,
"count": 5,
"self": 18.017423858000257
}
}
},
"_update_policy": {
"total": 189.42771329799962,
"count": 48,
"self": 126.5529493140175,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.87476398398212,
"count": 1440,
"self": 62.87476398398212
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.979994501918554e-07,
"count": 1,
"self": 9.979994501918554e-07
},
"TrainerController._save_models": {
"total": 1.1758522300006007,
"count": 1,
"self": 0.0316458520010201,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1442063779995806,
"count": 1,
"self": 1.1442063779995806
}
}
}
}
}
}
}