ppo-Huggy / run_logs /timers.json
ojigrande's picture
Huggy runs for a stick.
acdab82 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.409204125404358,
"min": 1.409204125404358,
"max": 1.429154634475708,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69552.6796875,
"min": 69131.3203125,
"max": 77251.25,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 102.13991769547324,
"min": 80.03565640194489,
"max": 378.9398496240602,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49640.0,
"min": 48810.0,
"max": 50399.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999412.0,
"min": 49954.0,
"max": 1999412.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999412.0,
"min": 49954.0,
"max": 1999412.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.351675510406494,
"min": 0.171444371342659,
"max": 2.4640939235687256,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1142.914306640625,
"min": 22.630657196044922,
"max": 1456.6146240234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.5934425941955896,
"min": 1.7183765511621127,
"max": 4.022359990636716,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1746.4131007790565,
"min": 226.8257047533989,
"max": 2304.812274634838,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.5934425941955896,
"min": 1.7183765511621127,
"max": 4.022359990636716,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1746.4131007790565,
"min": 226.8257047533989,
"max": 2304.812274634838,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01739921877176837,
"min": 0.012916810534807154,
"max": 0.02041078147594817,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05219765631530511,
"min": 0.02583362106961431,
"max": 0.056409035314572975,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0490142667459117,
"min": 0.02148193839109606,
"max": 0.06224774105681313,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1470428002377351,
"min": 0.0470572205260396,
"max": 0.1867432231704394,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.450398849899994e-06,
"min": 3.450398849899994e-06,
"max": 0.0002953101015633,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0351196549699982e-05,
"min": 1.0351196549699982e-05,
"max": 0.0008440806186397999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10115009999999998,
"min": 0.10115009999999998,
"max": 0.19843670000000005,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30345029999999995,
"min": 0.20743495,
"max": 0.5813602,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.738998999999991e-05,
"min": 6.738998999999991e-05,
"max": 0.004921991329999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002021699699999997,
"min": 0.0002021699699999997,
"max": 0.014069873980000001,
"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": "1728572466",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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=Huggy2 --no-graphics",
"mlagents_version": "1.1.0",
"mlagents_envs_version": "1.1.0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0a0+81ea7a4",
"numpy_version": "1.23.5",
"end_time_seconds": "1728575127"
},
"total": 2660.8360765459947,
"count": 1,
"self": 0.31839961907826364,
"children": {
"run_training.setup": {
"total": 0.034530165838077664,
"count": 1,
"self": 0.034530165838077664
},
"TrainerController.start_learning": {
"total": 2660.4831467610784,
"count": 1,
"self": 4.231526987627149,
"children": {
"TrainerController._reset_env": {
"total": 1.5206520280335099,
"count": 1,
"self": 1.5206520280335099
},
"TrainerController.advance": {
"total": 2654.6516552644316,
"count": 231980,
"self": 4.769539019092917,
"children": {
"env_step": {
"total": 2365.6820681367535,
"count": 231980,
"self": 2066.14456870337,
"children": {
"SubprocessEnvManager._take_step": {
"total": 296.5384037962649,
"count": 231980,
"self": 11.667791423387825,
"children": {
"TorchPolicy.evaluate": {
"total": 284.8706123728771,
"count": 223004,
"self": 284.8706123728771
}
}
},
"workers": {
"total": 2.999095637118444,
"count": 231980,
"self": 0.0,
"children": {
"worker_root": {
"total": 2655.9692670137156,
"count": 231980,
"is_parallel": true,
"self": 774.6751236368436,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0005404921248555183,
"count": 1,
"is_parallel": true,
"self": 0.00016070203855633736,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000379790086299181,
"count": 2,
"is_parallel": true,
"self": 0.000379790086299181
}
}
},
"UnityEnvironment.step": {
"total": 0.028444795170798898,
"count": 1,
"is_parallel": true,
"self": 0.00010971818119287491,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003249659202992916,
"count": 1,
"is_parallel": true,
"self": 0.0003249659202992916
},
"communicator.exchange": {
"total": 0.027531218016520143,
"count": 1,
"is_parallel": true,
"self": 0.027531218016520143
},
"steps_from_proto": {
"total": 0.00047889305278658867,
"count": 1,
"is_parallel": true,
"self": 0.0001401691697537899,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00033872388303279877,
"count": 2,
"is_parallel": true,
"self": 0.00033872388303279877
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1881.294143376872,
"count": 231979,
"is_parallel": true,
"self": 15.236195259261876,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 154.0638051466085,
"count": 231979,
"is_parallel": true,
"self": 154.0638051466085
},
"communicator.exchange": {
"total": 1662.1403726544231,
"count": 231979,
"is_parallel": true,
"self": 1662.1403726544231
},
"steps_from_proto": {
"total": 49.85377031657845,
"count": 231979,
"is_parallel": true,
"self": 16.553676577750593,
"children": {
"_process_rank_one_or_two_observation": {
"total": 33.300093738827854,
"count": 463958,
"is_parallel": true,
"self": 33.300093738827854
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 284.2000481085852,
"count": 231980,
"self": 6.742239301092923,
"children": {
"process_trajectory": {
"total": 98.85826446698047,
"count": 231980,
"self": 97.99273678823374,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8655276787467301,
"count": 10,
"self": 0.8655276787467301
}
}
},
"_update_policy": {
"total": 178.59954434051178,
"count": 97,
"self": 141.61375643801875,
"children": {
"TorchPPOOptimizer.update": {
"total": 36.98578790249303,
"count": 2910,
"self": 36.98578790249303
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.885928213596344e-06,
"count": 1,
"self": 1.885928213596344e-06
},
"TrainerController._save_models": {
"total": 0.07931059505790472,
"count": 1,
"self": 0.001976103987544775,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07733449107035995,
"count": 1,
"self": 0.07733449107035995
}
}
}
}
}
}
}