ppo-Huggy / run_logs /timers.json
mkx07's picture
Huggy
d55c95f verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4104092121124268,
"min": 1.4104092121124268,
"max": 1.4280914068222046,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 71208.7421875,
"min": 69481.484375,
"max": 77332.8515625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 79.10416666666667,
"min": 76.18181818181819,
"max": 412.78512396694214,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49361.0,
"min": 48747.0,
"max": 50073.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999888.0,
"min": 49858.0,
"max": 1999888.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999888.0,
"min": 49858.0,
"max": 1999888.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.439754009246826,
"min": 0.05018286779522896,
"max": 2.4742307662963867,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1522.406494140625,
"min": 6.021944046020508,
"max": 1577.65771484375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.808569810233819,
"min": 1.6890708208084106,
"max": 3.9583080676885753,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2376.547561585903,
"min": 202.68849849700928,
"max": 2487.376227378845,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.808569810233819,
"min": 1.6890708208084106,
"max": 3.9583080676885753,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2376.547561585903,
"min": 202.68849849700928,
"max": 2487.376227378845,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.01590273223021844,
"min": 0.012052477867049067,
"max": 0.018867078054851542,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04770819669065532,
"min": 0.024104955734098134,
"max": 0.05234250731688614,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05605962959428629,
"min": 0.021640020484725634,
"max": 0.0618772721538941,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16817888878285886,
"min": 0.04328004096945127,
"max": 0.17392601830263932,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.650748783116666e-06,
"min": 3.650748783116666e-06,
"max": 0.00029532412655862504,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.0952246349349998e-05,
"min": 1.0952246349349998e-05,
"max": 0.00084385366871545,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10121688333333334,
"min": 0.10121688333333334,
"max": 0.19844137499999998,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30365065,
"min": 0.20756779999999994,
"max": 0.5812845499999999,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.072247833333333e-05,
"min": 7.072247833333333e-05,
"max": 0.004922224612500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.000212167435,
"min": 0.000212167435,
"max": 0.014066099045000002,
"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": "1745471396",
"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 --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": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1745473897"
},
"total": 2501.43821552,
"count": 1,
"self": 0.43821173800006363,
"children": {
"run_training.setup": {
"total": 0.023104872999965664,
"count": 1,
"self": 0.023104872999965664
},
"TrainerController.start_learning": {
"total": 2500.9768989090003,
"count": 1,
"self": 4.4606306409609715,
"children": {
"TrainerController._reset_env": {
"total": 3.3376610069999515,
"count": 1,
"self": 3.3376610069999515
},
"TrainerController.advance": {
"total": 2493.06788021804,
"count": 232970,
"self": 4.790467863941558,
"children": {
"env_step": {
"total": 1993.2387942600399,
"count": 232970,
"self": 1570.7308626379954,
"children": {
"SubprocessEnvManager._take_step": {
"total": 419.8701343560192,
"count": 232970,
"self": 15.936649278138248,
"children": {
"TorchPolicy.evaluate": {
"total": 403.93348507788096,
"count": 222969,
"self": 403.93348507788096
}
}
},
"workers": {
"total": 2.6377972660252453,
"count": 232970,
"self": 0.0,
"children": {
"worker_root": {
"total": 2493.307821620039,
"count": 232970,
"is_parallel": true,
"self": 1214.5805756650202,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009529150001981179,
"count": 1,
"is_parallel": true,
"self": 0.00027911400025004696,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000673800999948071,
"count": 2,
"is_parallel": true,
"self": 0.000673800999948071
}
}
},
"UnityEnvironment.step": {
"total": 0.03237096000020756,
"count": 1,
"is_parallel": true,
"self": 0.00034721800011539017,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002018150000822061,
"count": 1,
"is_parallel": true,
"self": 0.0002018150000822061
},
"communicator.exchange": {
"total": 0.031132880999848567,
"count": 1,
"is_parallel": true,
"self": 0.031132880999848567
},
"steps_from_proto": {
"total": 0.0006890460001613974,
"count": 1,
"is_parallel": true,
"self": 0.00020342300012998749,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004856230000314099,
"count": 2,
"is_parallel": true,
"self": 0.0004856230000314099
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1278.7272459550186,
"count": 232969,
"is_parallel": true,
"self": 37.90043237995178,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 83.3137315229767,
"count": 232969,
"is_parallel": true,
"self": 83.3137315229767
},
"communicator.exchange": {
"total": 1067.3598023430914,
"count": 232969,
"is_parallel": true,
"self": 1067.3598023430914
},
"steps_from_proto": {
"total": 90.15327970899875,
"count": 232969,
"is_parallel": true,
"self": 34.1250294771105,
"children": {
"_process_rank_one_or_two_observation": {
"total": 56.02825023188825,
"count": 465938,
"is_parallel": true,
"self": 56.02825023188825
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 495.0386180940586,
"count": 232970,
"self": 6.309437536028099,
"children": {
"process_trajectory": {
"total": 170.36814001503035,
"count": 232970,
"self": 169.12906107303024,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2390789420001056,
"count": 10,
"self": 1.2390789420001056
}
}
},
"_update_policy": {
"total": 318.3610405430002,
"count": 97,
"self": 255.4656349890024,
"children": {
"TorchPPOOptimizer.update": {
"total": 62.89540555399776,
"count": 2910,
"self": 62.89540555399776
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.769992175279185e-07,
"count": 1,
"self": 9.769992175279185e-07
},
"TrainerController._save_models": {
"total": 0.11072606600009749,
"count": 1,
"self": 0.0015822020004634396,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10914386399963405,
"count": 1,
"self": 0.10914386399963405
}
}
}
}
}
}
}