ppo-Huggy / run_logs /timers.json
Kenemo's picture
Huggy is fun
53d519f
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4304486513137817,
"min": 1.4191831350326538,
"max": 1.4304486513137817,
"count": 5
},
"Huggy.Policy.Entropy.sum": {
"value": 71593.953125,
"min": 68872.703125,
"max": 76508.1640625,
"count": 5
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 192.6796875,
"min": 192.6796875,
"max": 426.4957264957265,
"count": 5
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49326.0,
"min": 49326.0,
"max": 50046.0,
"count": 5
},
"Huggy.Step.mean": {
"value": 249821.0,
"min": 49362.0,
"max": 249821.0,
"count": 5
},
"Huggy.Step.sum": {
"value": 249821.0,
"min": 49362.0,
"max": 249821.0,
"count": 5
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 1.1035908460617065,
"min": 0.011492632329463959,
"max": 1.1035908460617065,
"count": 5
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 282.5192565917969,
"min": 1.3331453800201416,
"max": 282.5192565917969,
"count": 5
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.3420118254143745,
"min": 1.8491729136941761,
"max": 3.3420118254143745,
"count": 5
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 855.5550273060799,
"min": 214.50405798852444,
"max": 855.5550273060799,
"count": 5
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.3420118254143745,
"min": 1.8491729136941761,
"max": 3.3420118254143745,
"count": 5
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 855.5550273060799,
"min": 214.50405798852444,
"max": 855.5550273060799,
"count": 5
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017022319691184545,
"min": 0.016135072868079685,
"max": 0.019427459776246297,
"count": 5
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05106695907355363,
"min": 0.03227014573615937,
"max": 0.05106695907355363,
"count": 5
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.02850977114091317,
"min": 0.021749750679979724,
"max": 0.03098703467597564,
"count": 5
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.0855293134227395,
"min": 0.04349950135995945,
"max": 0.0855293134227395,
"count": 5
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.0002659298613567167,
"min": 0.0002659298613567167,
"max": 0.00029529442656852495,
"count": 5
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.00079778958407015,
"min": 0.00054725116758295,
"max": 0.00084407026864325,
"count": 5
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.18864328333333333,
"min": 0.18864328333333333,
"max": 0.19843147500000002,
"count": 5
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.56592985,
"min": 0.38241705000000004,
"max": 0.5813567499999999,
"count": 5
},
"Huggy.Policy.Beta.mean": {
"value": 0.004433299838333333,
"min": 0.004433299838333333,
"max": 0.004921730602499999,
"count": 5
},
"Huggy.Policy.Beta.sum": {
"value": 0.013299899515,
"min": 0.009122610795000001,
"max": 0.014069701824999996,
"count": 5
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1674575056",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674575338"
},
"total": 282.175534797,
"count": 1,
"self": 0.23005776700000524,
"children": {
"run_training.setup": {
"total": 0.10780774899998846,
"count": 1,
"self": 0.10780774899998846
},
"TrainerController.start_learning": {
"total": 281.837669281,
"count": 1,
"self": 0.48528997300013543,
"children": {
"TrainerController._reset_env": {
"total": 10.146381300000002,
"count": 1,
"self": 10.146381300000002
},
"TrainerController.advance": {
"total": 271.0048912319999,
"count": 29807,
"self": 0.5422386940023785,
"children": {
"env_step": {
"total": 218.77537035199953,
"count": 29807,
"self": 182.74931759000492,
"children": {
"SubprocessEnvManager._take_step": {
"total": 35.71163078999791,
"count": 29807,
"self": 1.8802147269960017,
"children": {
"TorchPolicy.evaluate": {
"total": 33.83141606300191,
"count": 29346,
"self": 8.33162522500146,
"children": {
"TorchPolicy.sample_actions": {
"total": 25.49979083800045,
"count": 29346,
"self": 25.49979083800045
}
}
}
}
},
"workers": {
"total": 0.3144219719966941,
"count": 29806,
"self": 0.0,
"children": {
"worker_root": {
"total": 280.5092611730005,
"count": 29806,
"is_parallel": true,
"self": 131.12682022699704,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004530527000014217,
"count": 1,
"is_parallel": true,
"self": 0.00032587900003022696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.00420464799998399,
"count": 2,
"is_parallel": true,
"self": 0.00420464799998399
}
}
},
"UnityEnvironment.step": {
"total": 0.02761511799999994,
"count": 1,
"is_parallel": true,
"self": 0.00031849899997382636,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019876800001839,
"count": 1,
"is_parallel": true,
"self": 0.00019876800001839
},
"communicator.exchange": {
"total": 0.02617173699999853,
"count": 1,
"is_parallel": true,
"self": 0.02617173699999853
},
"steps_from_proto": {
"total": 0.0009261140000091928,
"count": 1,
"is_parallel": true,
"self": 0.00043201199997611184,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004941020000330809,
"count": 2,
"is_parallel": true,
"self": 0.0004941020000330809
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 149.38244094600344,
"count": 29805,
"is_parallel": true,
"self": 4.434515719001297,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 9.543731425997976,
"count": 29805,
"is_parallel": true,
"self": 9.543731425997976
},
"communicator.exchange": {
"total": 123.50528107099771,
"count": 29805,
"is_parallel": true,
"self": 123.50528107099771
},
"steps_from_proto": {
"total": 11.898912730006458,
"count": 29805,
"is_parallel": true,
"self": 4.720805587008613,
"children": {
"_process_rank_one_or_two_observation": {
"total": 7.178107142997845,
"count": 59610,
"is_parallel": true,
"self": 7.178107142997845
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 51.68728218599799,
"count": 29806,
"self": 0.8118623390036817,
"children": {
"process_trajectory": {
"total": 14.264102905994264,
"count": 29806,
"self": 14.151825161994282,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11227774399998225,
"count": 1,
"self": 0.11227774399998225
}
}
},
"_update_policy": {
"total": 36.61131694100004,
"count": 12,
"self": 30.11693464999985,
"children": {
"TorchPPOOptimizer.update": {
"total": 6.494382291000193,
"count": 360,
"self": 6.494382291000193
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.2309999988247e-06,
"count": 1,
"self": 1.2309999988247e-06
},
"TrainerController._save_models": {
"total": 0.2011055449999617,
"count": 1,
"self": 0.0026931680000075175,
"children": {
"RLTrainer._checkpoint": {
"total": 0.19841237699995418,
"count": 1,
"self": 0.19841237699995418
}
}
}
}
}
}
}