ppo-Huggy / run_logs /timers.json
eyac's picture
Huggy
87fe346 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.402599573135376,
"min": 1.402599573135376,
"max": 1.4269382953643799,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69742.859375,
"min": 67291.7421875,
"max": 76094.7421875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 72.06286549707602,
"min": 68.88826815642459,
"max": 423.06779661016947,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49291.0,
"min": 49210.0,
"max": 50054.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999965.0,
"min": 49701.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999965.0,
"min": 49701.0,
"max": 1999965.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.518839120864868,
"min": 0.06320351362228394,
"max": 2.5367212295532227,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1722.885986328125,
"min": 7.394810676574707,
"max": 1779.127685546875,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9564679911610674,
"min": 1.7989348450150244,
"max": 4.066943482798938,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2706.22410595417,
"min": 210.47537686675787,
"max": 2818.4692783355713,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9564679911610674,
"min": 1.7989348450150244,
"max": 4.066943482798938,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2706.22410595417,
"min": 210.47537686675787,
"max": 2818.4692783355713,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01495263414463908,
"min": 0.013640643984156972,
"max": 0.019890359990919627,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04485790243391724,
"min": 0.027281287968313944,
"max": 0.0567879542107524,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06544200864930948,
"min": 0.02043555437897642,
"max": 0.06544200864930948,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.19632602594792842,
"min": 0.04087110875795284,
"max": 0.19632602594792842,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.7247487584500063e-06,
"min": 3.7247487584500063e-06,
"max": 0.0002952609015797,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.117424627535002e-05,
"min": 1.117424627535002e-05,
"max": 0.0008437528687490498,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10124155000000001,
"min": 0.10124155000000001,
"max": 0.19842030000000002,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30372465000000004,
"min": 0.20762965,
"max": 0.58125095,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.19533450000001e-05,
"min": 7.19533450000001e-05,
"max": 0.004921172969999999,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021586003500000033,
"min": 0.00021586003500000033,
"max": 0.014064422404999997,
"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": "1730645171",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.5.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1730647696"
},
"total": 2525.010363837,
"count": 1,
"self": 0.42501352799990855,
"children": {
"run_training.setup": {
"total": 0.05588795900007426,
"count": 1,
"self": 0.05588795900007426
},
"TrainerController.start_learning": {
"total": 2524.5294623500004,
"count": 1,
"self": 4.457551997077189,
"children": {
"TrainerController._reset_env": {
"total": 4.80520406200003,
"count": 1,
"self": 4.80520406200003
},
"TrainerController.advance": {
"total": 2515.1547116109227,
"count": 233672,
"self": 4.658945343745927,
"children": {
"env_step": {
"total": 1978.6490184650602,
"count": 233672,
"self": 1558.020164086084,
"children": {
"SubprocessEnvManager._take_step": {
"total": 417.8804495829752,
"count": 233672,
"self": 16.00105775993711,
"children": {
"TorchPolicy.evaluate": {
"total": 401.8793918230381,
"count": 222889,
"self": 401.8793918230381
}
}
},
"workers": {
"total": 2.7484047960010685,
"count": 233672,
"self": 0.0,
"children": {
"worker_root": {
"total": 2517.1943735598866,
"count": 233672,
"is_parallel": true,
"self": 1246.4555304488767,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008547899999484798,
"count": 1,
"is_parallel": true,
"self": 0.0002681199996459327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005866700003025471,
"count": 2,
"is_parallel": true,
"self": 0.0005866700003025471
}
}
},
"UnityEnvironment.step": {
"total": 0.03057731099988814,
"count": 1,
"is_parallel": true,
"self": 0.0004070789998422697,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002025900000717229,
"count": 1,
"is_parallel": true,
"self": 0.0002025900000717229
},
"communicator.exchange": {
"total": 0.029182945999991716,
"count": 1,
"is_parallel": true,
"self": 0.029182945999991716
},
"steps_from_proto": {
"total": 0.0007846959999824321,
"count": 1,
"is_parallel": true,
"self": 0.00020666799991886364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005780280000635685,
"count": 2,
"is_parallel": true,
"self": 0.0005780280000635685
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1270.7388431110098,
"count": 233671,
"is_parallel": true,
"self": 38.24419279522954,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 85.01379388283772,
"count": 233671,
"is_parallel": true,
"self": 85.01379388283772
},
"communicator.exchange": {
"total": 1056.8839251779725,
"count": 233671,
"is_parallel": true,
"self": 1056.8839251779725
},
"steps_from_proto": {
"total": 90.59693125497006,
"count": 233671,
"is_parallel": true,
"self": 34.35543341401831,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.24149784095175,
"count": 467342,
"is_parallel": true,
"self": 56.24149784095175
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 531.8467478021169,
"count": 233672,
"self": 6.5906175302072825,
"children": {
"process_trajectory": {
"total": 181.62654639190623,
"count": 233672,
"self": 180.26253827390565,
"children": {
"RLTrainer._checkpoint": {
"total": 1.3640081180005836,
"count": 10,
"self": 1.3640081180005836
}
}
},
"_update_policy": {
"total": 343.62958388000334,
"count": 97,
"self": 277.63649058900637,
"children": {
"TorchPPOOptimizer.update": {
"total": 65.99309329099697,
"count": 2910,
"self": 65.99309329099697
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.899999895424116e-07,
"count": 1,
"self": 9.899999895424116e-07
},
"TrainerController._save_models": {
"total": 0.1119936900004177,
"count": 1,
"self": 0.0019983410002168966,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1099953490002008,
"count": 1,
"self": 0.1099953490002008
}
}
}
}
}
}
}