ppo-Huggy / run_logs /timers.json
nanxsu's picture
Huggy
77c81de verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4116944074630737,
"min": 1.4116944074630737,
"max": 1.4284054040908813,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71643.4921875,
"min": 69187.1875,
"max": 77555.671875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 95.66795366795367,
"min": 95.66795366795367,
"max": 445.6637168141593,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49556.0,
"min": 48965.0,
"max": 50360.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999961.0,
"min": 49767.0,
"max": 1999961.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999961.0,
"min": 49767.0,
"max": 1999961.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.3879220485687256,
"min": 0.07708744704723358,
"max": 2.4208266735076904,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1236.943603515625,
"min": 8.633793830871582,
"max": 1236.943603515625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.71119956160144,
"min": 1.7637484754834856,
"max": 3.7951039943364586,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1922.401372909546,
"min": 197.5398292541504,
"max": 1922.401372909546,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.71119956160144,
"min": 1.7637484754834856,
"max": 3.7951039943364586,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1922.401372909546,
"min": 197.5398292541504,
"max": 1922.401372909546,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01555218729142022,
"min": 0.012352857365234135,
"max": 0.020695336040161137,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03110437458284044,
"min": 0.02470571473046827,
"max": 0.06208600812048341,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05597734556843838,
"min": 0.0215901975830396,
"max": 0.05597734556843838,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.11195469113687675,
"min": 0.0431803951660792,
"max": 0.16468291332324347,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.487948504050003e-06,
"min": 4.487948504050003e-06,
"max": 0.0002952867015711,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.975897008100007e-06,
"min": 8.975897008100007e-06,
"max": 0.0008440908186363999,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10149595000000003,
"min": 0.10149595000000003,
"max": 0.19842890000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20299190000000006,
"min": 0.20299190000000006,
"max": 0.5813636,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.464790500000009e-05,
"min": 8.464790500000009e-05,
"max": 0.004921602109999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016929581000000018,
"min": 0.00016929581000000018,
"max": 0.01407004364,
"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": "1716563507",
"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.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1716566010"
},
"total": 2502.993628419,
"count": 1,
"self": 0.7537700869993387,
"children": {
"run_training.setup": {
"total": 0.05373383300002388,
"count": 1,
"self": 0.05373383300002388
},
"TrainerController.start_learning": {
"total": 2502.1861244990005,
"count": 1,
"self": 4.682127282985675,
"children": {
"TrainerController._reset_env": {
"total": 3.4664032090000205,
"count": 1,
"self": 3.4664032090000205
},
"TrainerController.advance": {
"total": 2493.864223488015,
"count": 231101,
"self": 4.864978995996353,
"children": {
"env_step": {
"total": 1997.8415199060382,
"count": 231101,
"self": 1644.7410638917893,
"children": {
"SubprocessEnvManager._take_step": {
"total": 350.07693437707707,
"count": 231101,
"self": 17.130033596133217,
"children": {
"TorchPolicy.evaluate": {
"total": 332.94690078094385,
"count": 222985,
"self": 332.94690078094385
}
}
},
"workers": {
"total": 3.023521637171939,
"count": 231101,
"self": 0.0,
"children": {
"worker_root": {
"total": 2494.4685288879255,
"count": 231101,
"is_parallel": true,
"self": 1173.5305410427923,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0010170749999929285,
"count": 1,
"is_parallel": true,
"self": 0.0002821139999582556,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007349610000346729,
"count": 2,
"is_parallel": true,
"self": 0.0007349610000346729
}
}
},
"UnityEnvironment.step": {
"total": 0.03145466400002306,
"count": 1,
"is_parallel": true,
"self": 0.0003948240000113401,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002114699999538061,
"count": 1,
"is_parallel": true,
"self": 0.0002114699999538061
},
"communicator.exchange": {
"total": 0.030069935000028636,
"count": 1,
"is_parallel": true,
"self": 0.030069935000028636
},
"steps_from_proto": {
"total": 0.0007784350000292761,
"count": 1,
"is_parallel": true,
"self": 0.0002220400000396694,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005563949999896067,
"count": 2,
"is_parallel": true,
"self": 0.0005563949999896067
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1320.9379878451332,
"count": 231100,
"is_parallel": true,
"self": 39.87011803812402,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 86.61301973701063,
"count": 231100,
"is_parallel": true,
"self": 86.61301973701063
},
"communicator.exchange": {
"total": 1101.2657174640478,
"count": 231100,
"is_parallel": true,
"self": 1101.2657174640478
},
"steps_from_proto": {
"total": 93.18913260595076,
"count": 231100,
"is_parallel": true,
"self": 35.454184212766734,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.73494839318403,
"count": 462200,
"is_parallel": true,
"self": 57.73494839318403
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 491.1577245859805,
"count": 231101,
"self": 6.788974631970689,
"children": {
"process_trajectory": {
"total": 157.01473481300832,
"count": 231101,
"self": 155.63718182400885,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3775529889994687,
"count": 10,
"self": 1.3775529889994687
}
}
},
"_update_policy": {
"total": 327.35401514100147,
"count": 96,
"self": 263.6302748570098,
"children": {
"TorchPPOOptimizer.update": {
"total": 63.723740283991674,
"count": 2880,
"self": 63.723740283991674
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.36500011649332e-06,
"count": 1,
"self": 1.36500011649332e-06
},
"TrainerController._save_models": {
"total": 0.173369153999829,
"count": 1,
"self": 0.0030163890000949323,
"children": {
"RLTrainer._checkpoint": {
"total": 0.17035276499973406,
"count": 1,
"self": 0.17035276499973406
}
}
}
}
}
}
}