ppo-Huggy / run_logs /timers.json
ajankelo's picture
Huggy
ff3adf7
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4109364748001099,
"min": 1.4109364748001099,
"max": 1.4299918413162231,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71705.203125,
"min": 68014.421875,
"max": 76752.5859375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 106.00426439232409,
"min": 89.82851985559567,
"max": 394.07086614173227,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49716.0,
"min": 48802.0,
"max": 50239.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999472.0,
"min": 49937.0,
"max": 1999472.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999472.0,
"min": 49937.0,
"max": 1999472.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.349482536315918,
"min": 0.0416354276239872,
"max": 2.4120476245880127,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1101.9073486328125,
"min": 5.246063709259033,
"max": 1332.432861328125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.636859419249268,
"min": 1.920176393928982,
"max": 3.897252770975746,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1705.6870676279068,
"min": 241.94222563505173,
"max": 2067.518074929714,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.636859419249268,
"min": 1.920176393928982,
"max": 3.897252770975746,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1705.6870676279068,
"min": 241.94222563505173,
"max": 2067.518074929714,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015736284097794043,
"min": 0.012641538590603178,
"max": 0.01960959001735318,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04720885229338213,
"min": 0.027487092124162397,
"max": 0.05882877005205955,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04950511318941911,
"min": 0.02315325131639838,
"max": 0.06828465685248375,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14851533956825733,
"min": 0.04630650263279676,
"max": 0.20485397055745125,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.1535989488333315e-06,
"min": 3.1535989488333315e-06,
"max": 0.0002953542015486,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.460796846499994e-06,
"min": 9.460796846499994e-06,
"max": 0.0008443086185638,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10105116666666668,
"min": 0.10105116666666668,
"max": 0.19845140000000006,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3031535,
"min": 0.20723354999999996,
"max": 0.5814362,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.245321666666663e-05,
"min": 6.245321666666663e-05,
"max": 0.004922724860000001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0001873596499999999,
"min": 0.0001873596499999999,
"max": 0.01407366638,
"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": "1679024780",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \n[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": "1679026811"
},
"total": 2030.9601223199998,
"count": 1,
"self": 0.32432344600010765,
"children": {
"run_training.setup": {
"total": 0.10108345899993765,
"count": 1,
"self": 0.10108345899993765
},
"TrainerController.start_learning": {
"total": 2030.5347154149997,
"count": 1,
"self": 4.072277839107983,
"children": {
"TrainerController._reset_env": {
"total": 5.965666512000098,
"count": 1,
"self": 5.965666512000098
},
"TrainerController.advance": {
"total": 2020.3828183108917,
"count": 231922,
"self": 4.305988102950778,
"children": {
"env_step": {
"total": 1575.1984243708623,
"count": 231922,
"self": 1304.679440336847,
"children": {
"SubprocessEnvManager._take_step": {
"total": 267.81566698602114,
"count": 231922,
"self": 16.07490335713601,
"children": {
"TorchPolicy.evaluate": {
"total": 251.74076362888513,
"count": 223008,
"self": 251.74076362888513
}
}
},
"workers": {
"total": 2.703317047994233,
"count": 231922,
"self": 0.0,
"children": {
"worker_root": {
"total": 2021.9024384289123,
"count": 231922,
"is_parallel": true,
"self": 976.5821128058997,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008347109999249369,
"count": 1,
"is_parallel": true,
"self": 0.0002531069999349711,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005816039999899658,
"count": 2,
"is_parallel": true,
"self": 0.0005816039999899658
}
}
},
"UnityEnvironment.step": {
"total": 0.03147856900000079,
"count": 1,
"is_parallel": true,
"self": 0.00035801600006379886,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019980599995506054,
"count": 1,
"is_parallel": true,
"self": 0.00019980599995506054
},
"communicator.exchange": {
"total": 0.030140327000026446,
"count": 1,
"is_parallel": true,
"self": 0.030140327000026446
},
"steps_from_proto": {
"total": 0.0007804199999554839,
"count": 1,
"is_parallel": true,
"self": 0.0002771770000435936,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005032429999118904,
"count": 2,
"is_parallel": true,
"self": 0.0005032429999118904
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1045.3203256230126,
"count": 231921,
"is_parallel": true,
"self": 32.13494057313642,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 63.00163592204717,
"count": 231921,
"is_parallel": true,
"self": 63.00163592204717
},
"communicator.exchange": {
"total": 875.224684577948,
"count": 231921,
"is_parallel": true,
"self": 875.224684577948
},
"steps_from_proto": {
"total": 74.95906454988108,
"count": 231921,
"is_parallel": true,
"self": 30.328472316063653,
"children": {
"_process_rank_one_or_two_observation": {
"total": 44.630592233817424,
"count": 463842,
"is_parallel": true,
"self": 44.630592233817424
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 440.8784058370786,
"count": 231922,
"self": 6.126688808085191,
"children": {
"process_trajectory": {
"total": 125.43600614199408,
"count": 231922,
"self": 124.26523863099351,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1707675110005766,
"count": 10,
"self": 1.1707675110005766
}
}
},
"_update_policy": {
"total": 309.31571088699934,
"count": 97,
"self": 254.82800411100857,
"children": {
"TorchPPOOptimizer.update": {
"total": 54.48770677599077,
"count": 2910,
"self": 54.48770677599077
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0500002645130735e-06,
"count": 1,
"self": 1.0500002645130735e-06
},
"TrainerController._save_models": {
"total": 0.11395170299965685,
"count": 1,
"self": 0.002182302999699459,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11176939999995739,
"count": 1,
"self": 0.11176939999995739
}
}
}
}
}
}
}