ppo-Huggy / run_logs /timers.json
AlexandreManai's picture
Huggy
36da6e9 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4047714471817017,
"min": 1.4047714471817017,
"max": 1.4260005950927734,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70317.2421875,
"min": 68918.7734375,
"max": 77375.4921875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 104.30315789473684,
"min": 94.42557251908397,
"max": 415.89166666666665,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49544.0,
"min": 48938.0,
"max": 50149.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999940.0,
"min": 49897.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999940.0,
"min": 49897.0,
"max": 1999940.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.349289655685425,
"min": 0.046666763722896576,
"max": 2.3931686878204346,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1115.91259765625,
"min": 5.5533447265625,
"max": 1210.337158203125,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.6281067269726806,
"min": 1.8829667116163158,
"max": 3.898710249983443,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1723.3506953120232,
"min": 224.07303868234158,
"max": 1955.2505713105202,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.6281067269726806,
"min": 1.8829667116163158,
"max": 3.898710249983443,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1723.3506953120232,
"min": 224.07303868234158,
"max": 1955.2505713105202,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01834063763769033,
"min": 0.011643477074297456,
"max": 0.01924978330450055,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05502191291307099,
"min": 0.027433147799941555,
"max": 0.05767837642827847,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.04822680349979136,
"min": 0.02190004338820775,
"max": 0.05215935415277878,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.14468041049937408,
"min": 0.0438000867764155,
"max": 0.15357678557435672,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.2046489318166617e-06,
"min": 3.2046489318166617e-06,
"max": 0.000295375576541475,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 9.613946795449985e-06,
"min": 9.613946795449985e-06,
"max": 0.00084444286851905,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10106818333333333,
"min": 0.10106818333333333,
"max": 0.198458525,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30320454999999996,
"min": 0.20729944999999997,
"max": 0.5814809499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 6.330234833333325e-05,
"min": 6.330234833333325e-05,
"max": 0.004923080397500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00018990704499999975,
"min": 0.00018990704499999975,
"max": 0.014075899405,
"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": "1709584217",
"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": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1709586525"
},
"total": 2308.4296906769996,
"count": 1,
"self": 0.4394856839994645,
"children": {
"run_training.setup": {
"total": 0.04876323999997112,
"count": 1,
"self": 0.04876323999997112
},
"TrainerController.start_learning": {
"total": 2307.941441753,
"count": 1,
"self": 4.313682701990729,
"children": {
"TrainerController._reset_env": {
"total": 3.152411387000029,
"count": 1,
"self": 3.152411387000029
},
"TrainerController.advance": {
"total": 2300.3571461800093,
"count": 231290,
"self": 4.773549156999707,
"children": {
"env_step": {
"total": 1831.1161971700008,
"count": 231290,
"self": 1517.645899602992,
"children": {
"SubprocessEnvManager._take_step": {
"total": 310.8342334350598,
"count": 231290,
"self": 16.91708940204171,
"children": {
"TorchPolicy.evaluate": {
"total": 293.9171440330181,
"count": 222976,
"self": 293.9171440330181
}
}
},
"workers": {
"total": 2.6360641319490696,
"count": 231290,
"self": 0.0,
"children": {
"worker_root": {
"total": 2300.9474834280068,
"count": 231290,
"is_parallel": true,
"self": 1061.6172323390933,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009072630000446225,
"count": 1,
"is_parallel": true,
"self": 0.00022197800012691005,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006852849999177124,
"count": 2,
"is_parallel": true,
"self": 0.0006852849999177124
}
}
},
"UnityEnvironment.step": {
"total": 0.02953809900009219,
"count": 1,
"is_parallel": true,
"self": 0.00035278200004995597,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002177530000153638,
"count": 1,
"is_parallel": true,
"self": 0.0002177530000153638
},
"communicator.exchange": {
"total": 0.02824054100005924,
"count": 1,
"is_parallel": true,
"self": 0.02824054100005924
},
"steps_from_proto": {
"total": 0.0007270229999676303,
"count": 1,
"is_parallel": true,
"self": 0.000193988999967587,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005330340000000433,
"count": 2,
"is_parallel": true,
"self": 0.0005330340000000433
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1239.3302510889134,
"count": 231289,
"is_parallel": true,
"self": 40.455379715939216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 81.89858821703604,
"count": 231289,
"is_parallel": true,
"self": 81.89858821703604
},
"communicator.exchange": {
"total": 1027.225590673902,
"count": 231289,
"is_parallel": true,
"self": 1027.225590673902
},
"steps_from_proto": {
"total": 89.75069248203636,
"count": 231289,
"is_parallel": true,
"self": 31.380195039942123,
"children": {
"_process_rank_one_or_two_observation": {
"total": 58.37049744209423,
"count": 462578,
"is_parallel": true,
"self": 58.37049744209423
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 464.46739985300894,
"count": 231290,
"self": 6.481532817010475,
"children": {
"process_trajectory": {
"total": 142.95078207199936,
"count": 231290,
"self": 141.74884451999947,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2019375519998903,
"count": 10,
"self": 1.2019375519998903
}
}
},
"_update_policy": {
"total": 315.0350849639991,
"count": 97,
"self": 252.7957456680008,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.23933929599832,
"count": 2910,
"self": 62.23933929599832
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.230003913922701e-07,
"count": 1,
"self": 8.230003913922701e-07
},
"TrainerController._save_models": {
"total": 0.11820066099971882,
"count": 1,
"self": 0.0029472979995261994,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11525336300019262,
"count": 1,
"self": 0.11525336300019262
}
}
}
}
}
}
}