ppo-Huggy / run_logs /timers.json
osanseviero's picture
Huggy
a776511
raw
history blame
17.9 kB
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4065452814102173,
"min": 1.4065452814102173,
"max": 1.4263813495635986,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70266.78125,
"min": 67836.03125,
"max": 77496.1015625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 73.06666666666666,
"min": 70.73744619799139,
"max": 404.9596774193548,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49320.0,
"min": 48927.0,
"max": 50215.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999989.0,
"min": 49806.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999989.0,
"min": 49806.0,
"max": 1999989.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.51290225982666,
"min": 0.0962253138422966,
"max": 2.5379412174224854,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1696.208984375,
"min": 11.835713386535645,
"max": 1739.334716796875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.904644805325402,
"min": 1.7523136287927628,
"max": 4.084090271422533,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2635.6352435946465,
"min": 215.53457634150982,
"max": 2750.6334089040756,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.904644805325402,
"min": 1.7523136287927628,
"max": 4.084090271422533,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2635.6352435946465,
"min": 215.53457634150982,
"max": 2750.6334089040756,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015798337165284063,
"min": 0.012170993952834882,
"max": 0.021318588617335384,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.047395011495852186,
"min": 0.024341987905669764,
"max": 0.05707367788612222,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06340437473522292,
"min": 0.021673926152288914,
"max": 0.06340437473522292,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19021312420566877,
"min": 0.04334785230457783,
"max": 0.19021312420566877,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.953448682216667e-06,
"min": 3.953448682216667e-06,
"max": 0.00029529142656952497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.186034604665e-05,
"min": 1.186034604665e-05,
"max": 0.0008440650186449999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10131778333333334,
"min": 0.10131778333333334,
"max": 0.198430475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30395335,
"min": 0.20776545000000002,
"max": 0.5813550000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.575738833333336e-05,
"min": 7.575738833333336e-05,
"max": 0.0049216807025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022727216500000006,
"min": 0.00022727216500000006,
"max": 0.014069614500000004,
"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": "1670241092",
"python_version": "3.8.15 (default, Oct 12 2022, 19:14:39) \n[GCC 7.5.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn /content/ml-agents/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": "1670243526"
},
"total": 2434.420895751,
"count": 1,
"self": 0.39472936499987554,
"children": {
"run_training.setup": {
"total": 0.11796321999997872,
"count": 1,
"self": 0.11796321999997872
},
"TrainerController.start_learning": {
"total": 2433.908203166,
"count": 1,
"self": 4.533720889029155,
"children": {
"TrainerController._reset_env": {
"total": 10.49349715400001,
"count": 1,
"self": 10.49349715400001
},
"TrainerController.advance": {
"total": 2418.7490553539706,
"count": 233370,
"self": 4.854657397103892,
"children": {
"env_step": {
"total": 1920.883818028919,
"count": 233370,
"self": 1605.824678502884,
"children": {
"SubprocessEnvManager._take_step": {
"total": 312.08418232201836,
"count": 233370,
"self": 15.754219920986543,
"children": {
"TorchPolicy.evaluate": {
"total": 296.3299624010318,
"count": 222916,
"self": 73.86430036610523,
"children": {
"TorchPolicy.sample_actions": {
"total": 222.4656620349266,
"count": 222916,
"self": 222.4656620349266
}
}
}
}
},
"workers": {
"total": 2.9749572040167322,
"count": 233370,
"self": 0.0,
"children": {
"worker_root": {
"total": 2425.176157149073,
"count": 233370,
"is_parallel": true,
"self": 1107.7586303690105,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.002272048999998333,
"count": 1,
"is_parallel": true,
"self": 0.00035362200003419275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019184269999641401,
"count": 2,
"is_parallel": true,
"self": 0.0019184269999641401
}
}
},
"UnityEnvironment.step": {
"total": 0.029071869999938826,
"count": 1,
"is_parallel": true,
"self": 0.0002766549999932977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0001969819999203537,
"count": 1,
"is_parallel": true,
"self": 0.0001969819999203537
},
"communicator.exchange": {
"total": 0.02776215400001547,
"count": 1,
"is_parallel": true,
"self": 0.02776215400001547
},
"steps_from_proto": {
"total": 0.000836079000009704,
"count": 1,
"is_parallel": true,
"self": 0.0002909390000240819,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005451399999856221,
"count": 2,
"is_parallel": true,
"self": 0.0005451399999856221
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1317.4175267800624,
"count": 233369,
"is_parallel": true,
"self": 37.48835860330041,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.38439815590459,
"count": 233369,
"is_parallel": true,
"self": 83.38439815590459
},
"communicator.exchange": {
"total": 1095.0802007128357,
"count": 233369,
"is_parallel": true,
"self": 1095.0802007128357
},
"steps_from_proto": {
"total": 101.46456930802174,
"count": 233369,
"is_parallel": true,
"self": 44.49087728514064,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.973692022881096,
"count": 466738,
"is_parallel": true,
"self": 56.973692022881096
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.01057992794756,
"count": 233370,
"self": 6.660378119920551,
"children": {
"process_trajectory": {
"total": 169.12415050202753,
"count": 233370,
"self": 168.6094649370275,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5146855650000361,
"count": 4,
"self": 0.5146855650000361
}
}
},
"_update_policy": {
"total": 317.2260513059995,
"count": 97,
"self": 262.76800949100436,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.45804181499511,
"count": 2910,
"self": 54.45804181499511
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.020000106829684e-07,
"count": 1,
"self": 9.020000106829684e-07
},
"TrainerController._save_models": {
"total": 0.1319288670001697,
"count": 1,
"self": 0.002114690000325936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12981417699984377,
"count": 1,
"self": 0.12981417699984377
}
}
}
}
}
}
}