ppo-Huggy / run_logs /timers.json
wowthecoder's picture
Huggy
427ca3b verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4090867042541504,
"min": 1.4090867042541504,
"max": 1.4263535737991333,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71521.015625,
"min": 68050.1640625,
"max": 76765.78125,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 113.76267281105991,
"min": 84.70205479452055,
"max": 414.1900826446281,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49373.0,
"min": 48934.0,
"max": 50117.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999908.0,
"min": 49569.0,
"max": 1999908.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999908.0,
"min": 49569.0,
"max": 1999908.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.294811964035034,
"min": 0.02730906382203102,
"max": 2.46648907661438,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 998.2431640625,
"min": 3.277087688446045,
"max": 1398.932373046875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3978680806598445,
"min": 1.71298786525925,
"max": 3.992218435787764,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1478.0726150870323,
"min": 205.55854383111,
"max": 2242.8872362971306,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3978680806598445,
"min": 1.71298786525925,
"max": 3.992218435787764,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1478.0726150870323,
"min": 205.55854383111,
"max": 2242.8872362971306,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.016728939266067756,
"min": 0.013331289520283462,
"max": 0.02152134929395591,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.03345787853213551,
"min": 0.026662579040566924,
"max": 0.06456404788186773,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04504740809400876,
"min": 0.02250251844525337,
"max": 0.056464677055676774,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.09009481618801753,
"min": 0.04500503689050674,
"max": 0.16725482220451038,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.443998518699989e-06,
"min": 4.443998518699989e-06,
"max": 0.00029523262658912497,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 8.887997037399978e-06,
"min": 8.887997037399978e-06,
"max": 0.0008435461688179499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10148129999999997,
"min": 0.10148129999999997,
"max": 0.198410875,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.20296259999999994,
"min": 0.20296259999999994,
"max": 0.5811820500000001,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 8.391686999999986e-05,
"min": 8.391686999999986e-05,
"max": 0.0049207026625,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00016783373999999972,
"min": 0.00016783373999999972,
"max": 0.014060984294999999,
"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": "1727305404",
"python_version": "3.10.12 (main, Sep 11 2024, 15:47:36) [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": "2.4.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1727307812"
},
"total": 2408.152435737,
"count": 1,
"self": 0.6332321179997962,
"children": {
"run_training.setup": {
"total": 0.052140099999974154,
"count": 1,
"self": 0.052140099999974154
},
"TrainerController.start_learning": {
"total": 2407.467063519,
"count": 1,
"self": 4.301731124905473,
"children": {
"TrainerController._reset_env": {
"total": 2.6024984100000665,
"count": 1,
"self": 2.6024984100000665
},
"TrainerController.advance": {
"total": 2400.3793899530942,
"count": 231923,
"self": 4.422967274072107,
"children": {
"env_step": {
"total": 1902.5611168049563,
"count": 231923,
"self": 1502.2637131310103,
"children": {
"SubprocessEnvManager._take_step": {
"total": 397.5944026290193,
"count": 231923,
"self": 15.573403299003985,
"children": {
"TorchPolicy.evaluate": {
"total": 382.02099933001534,
"count": 223028,
"self": 382.02099933001534
}
}
},
"workers": {
"total": 2.7030010449268502,
"count": 231923,
"self": 0.0,
"children": {
"worker_root": {
"total": 2399.9058893860292,
"count": 231923,
"is_parallel": true,
"self": 1184.4651098170348,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.000832468999988123,
"count": 1,
"is_parallel": true,
"self": 0.00020807299995340145,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006243960000347215,
"count": 2,
"is_parallel": true,
"self": 0.0006243960000347215
}
}
},
"UnityEnvironment.step": {
"total": 0.02789008100000956,
"count": 1,
"is_parallel": true,
"self": 0.0003588010001749353,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019383199992262234,
"count": 1,
"is_parallel": true,
"self": 0.00019383199992262234
},
"communicator.exchange": {
"total": 0.026591440999936822,
"count": 1,
"is_parallel": true,
"self": 0.026591440999936822
},
"steps_from_proto": {
"total": 0.0007460069999751795,
"count": 1,
"is_parallel": true,
"self": 0.00020850899989000027,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005374980000851792,
"count": 2,
"is_parallel": true,
"self": 0.0005374980000851792
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1215.4407795689945,
"count": 231922,
"is_parallel": true,
"self": 36.898159817074884,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 79.12096629595419,
"count": 231922,
"is_parallel": true,
"self": 79.12096629595419
},
"communicator.exchange": {
"total": 1012.4210987210264,
"count": 231922,
"is_parallel": true,
"self": 1012.4210987210264
},
"steps_from_proto": {
"total": 87.0005547349391,
"count": 231922,
"is_parallel": true,
"self": 30.827586539969502,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.1729681949696,
"count": 463844,
"is_parallel": true,
"self": 56.1729681949696
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 493.3953058740657,
"count": 231923,
"self": 6.348996448107641,
"children": {
"process_trajectory": {
"total": 161.84419875095523,
"count": 231923,
"self": 160.49682977695568,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3473689739995507,
"count": 10,
"self": 1.3473689739995507
}
}
},
"_update_policy": {
"total": 325.2021106750028,
"count": 96,
"self": 259.3425398269957,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.85957084800714,
"count": 2880,
"self": 65.85957084800714
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.5280002116924152e-06,
"count": 1,
"self": 1.5280002116924152e-06
},
"TrainerController._save_models": {
"total": 0.1834425030001512,
"count": 1,
"self": 0.002701502000036271,
"children": {
"RLTrainer._checkpoint": {
"total": 0.18074100100011492,
"count": 1,
"self": 0.18074100100011492
}
}
}
}
}
}
}