ppo-Huggy / run_logs /timers.json
jadericdawson's picture
Huggy
c5fed92 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.411191701889038,
"min": 1.4111573696136475,
"max": 1.4258347749710083,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 68638.953125,
"min": 56510.109375,
"max": 214048.5625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 89.18330308529946,
"min": 88.24113475177305,
"max": 359.86524822695037,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49140.0,
"min": 48911.0,
"max": 50741.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999992.0,
"min": 49819.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999992.0,
"min": 49819.0,
"max": 1999992.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.4110491275787354,
"min": 0.10015658289194107,
"max": 2.4110491275787354,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1338.1322021484375,
"min": 23.937423706054688,
"max": 1338.1322021484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8976754705111185,
"min": 1.6704717600195977,
"max": 4.007488208848077,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2163.209886133671,
"min": 277.8656502366066,
"max": 2163.209886133671,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8976754705111185,
"min": 1.6704717600195977,
"max": 4.007488208848077,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2163.209886133671,
"min": 277.8656502366066,
"max": 2163.209886133671,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018570126718259417,
"min": 0.013706788589171183,
"max": 0.019117550359320983,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03714025343651883,
"min": 0.02906119767697722,
"max": 0.057352651077962946,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05988243240863085,
"min": 0.01544542233977053,
"max": 0.05988243240863085,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1197648648172617,
"min": 0.0324017647964259,
"max": 0.16909866370260715,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.4424488525500006e-06,
"min": 3.4424488525500006e-06,
"max": 0.00029534310155229993,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 6.884897705100001e-06,
"min": 6.884897705100001e-06,
"max": 0.0008439087186971,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10114745,
"min": 0.10114745,
"max": 0.1984477,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.2022949,
"min": 0.2022949,
"max": 0.5813029000000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.7257755e-05,
"min": 6.7257755e-05,
"max": 0.0049225402299999995,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00013451551,
"min": 0.00013451551,
"max": 0.014067014710000002,
"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": "1739806579",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/Huggy.yaml --env=./trained-envs-executables/linux/Huggy/Huggy --num-env 25 --run-id=Huggy2 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1739809281"
},
"total": 2701.348648262001,
"count": 1,
"self": 5.871230885000841,
"children": {
"run_training.setup": {
"total": 1.972506770000109,
"count": 1,
"self": 1.972506770000109
},
"TrainerController.start_learning": {
"total": 2693.504910607,
"count": 1,
"self": 1.3631535709846503,
"children": {
"TrainerController._reset_env": {
"total": 19.644190913000784,
"count": 1,
"self": 19.644190913000784
},
"TrainerController.advance": {
"total": 2672.3317495630145,
"count": 10079,
"self": 0.43982863512064796,
"children": {
"env_step": {
"total": 1971.7755527529098,
"count": 10079,
"self": 652.1600494452723,
"children": {
"SubprocessEnvManager._take_step": {
"total": 1316.3417424357285,
"count": 233104,
"self": 43.89743963919682,
"children": {
"TorchPolicy.evaluate": {
"total": 1272.4443027965317,
"count": 226120,
"self": 1272.4443027965317
}
}
},
"workers": {
"total": 3.273760871908962,
"count": 10079,
"self": 0.0,
"children": {
"worker_root": {
"total": 67354.62647311323,
"count": 233098,
"is_parallel": true,
"self": 63408.25888207634,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.03994304900152201,
"count": 25,
"is_parallel": true,
"self": 0.014088166004512459,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.025854882997009554,
"count": 50,
"is_parallel": true,
"self": 0.025854882997009554
}
}
},
"UnityEnvironment.step": {
"total": 6.667764677999003,
"count": 25,
"is_parallel": true,
"self": 0.008390718994633062,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0046063290028541815,
"count": 25,
"is_parallel": true,
"self": 0.0046063290028541815
},
"communicator.exchange": {
"total": 6.616699996002353,
"count": 25,
"is_parallel": true,
"self": 6.616699996002353
},
"steps_from_proto": {
"total": 0.038067633999162354,
"count": 25,
"is_parallel": true,
"self": 0.013016539000091143,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.02505109499907121,
"count": 50,
"is_parallel": true,
"self": 0.02505109499907121
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 3946.367591036882,
"count": 233073,
"is_parallel": true,
"self": 58.727031490721856,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 106.86259871611219,
"count": 233073,
"is_parallel": true,
"self": 106.86259871611219
},
"communicator.exchange": {
"total": 3646.0508822709817,
"count": 233073,
"is_parallel": true,
"self": 3646.0508822709817
},
"steps_from_proto": {
"total": 134.72707855906629,
"count": 233073,
"is_parallel": true,
"self": 49.266219771368924,
"children": {
"_process_rank_one_or_two_observation": {
"total": 85.46085878769736,
"count": 466146,
"is_parallel": true,
"self": 85.46085878769736
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 700.116368174984,
"count": 10079,
"self": 3.563273589090386,
"children": {
"process_trajectory": {
"total": 245.88758710188995,
"count": 10079,
"self": 243.81780664088546,
"children": {
"RLTrainer._checkpoint": {
"total": 2.069780461004484,
"count": 10,
"self": 2.069780461004484
}
}
},
"_update_policy": {
"total": 450.6655074840037,
"count": 96,
"self": 359.0634578659283,
"children": {
"TorchPPOOptimizer.update": {
"total": 91.6020496180754,
"count": 2880,
"self": 91.6020496180754
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.7279999156016856e-06,
"count": 1,
"self": 1.7279999156016856e-06
},
"TrainerController._save_models": {
"total": 0.16581483200025104,
"count": 1,
"self": 0.0033219870001630625,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16249284500008798,
"count": 1,
"self": 0.16249284500008798
}
}
}
}
}
}
}