ppo-Huggy / run_logs /timers.json
vijmeister's picture
Huggy
7535fab
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.401203989982605,
"min": 1.401203989982605,
"max": 1.4261752367019653,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70327.828125,
"min": 68516.109375,
"max": 76470.234375,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 75.05022831050228,
"min": 74.05855855855856,
"max": 423.0504201680672,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49308.0,
"min": 49255.0,
"max": 50343.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999974.0,
"min": 49712.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999974.0,
"min": 49712.0,
"max": 1999974.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.487060070037842,
"min": 0.09293130785226822,
"max": 2.533316135406494,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1633.99853515625,
"min": 10.96589469909668,
"max": 1647.869140625,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.8779512703690897,
"min": 1.748378421290446,
"max": 4.074144863271792,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2547.813984632492,
"min": 206.30865371227264,
"max": 2628.003348827362,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.8779512703690897,
"min": 1.748378421290446,
"max": 4.074144863271792,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2547.813984632492,
"min": 206.30865371227264,
"max": 2628.003348827362,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.018237838893320358,
"min": 0.013524504489032552,
"max": 0.023320247194351395,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05471351667996108,
"min": 0.027049008978065104,
"max": 0.059339146209337446,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05927955321967602,
"min": 0.021368426581223808,
"max": 0.060222894822557764,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.17783865965902806,
"min": 0.042736853162447616,
"max": 0.17783865965902806,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.8777487074500006e-06,
"min": 3.8777487074500006e-06,
"max": 0.0002953827765390751,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1633246122350001e-05,
"min": 1.1633246122350001e-05,
"max": 0.00084384436871855,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10129255000000004,
"min": 0.10129255000000004,
"max": 0.198460925,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3038776500000001,
"min": 0.20771165000000008,
"max": 0.58128145,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.449824499999999e-05,
"min": 7.449824499999999e-05,
"max": 0.004923200157500001,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00022349473499999996,
"min": 0.00022349473499999996,
"max": 0.014065944355000002,
"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": "1680113668",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1680116037"
},
"total": 2368.624536564,
"count": 1,
"self": 0.4372801139998046,
"children": {
"run_training.setup": {
"total": 0.1135567350000315,
"count": 1,
"self": 0.1135567350000315
},
"TrainerController.start_learning": {
"total": 2368.073699715,
"count": 1,
"self": 4.295834595985525,
"children": {
"TrainerController._reset_env": {
"total": 9.838349283000014,
"count": 1,
"self": 9.838349283000014
},
"TrainerController.advance": {
"total": 2353.8185883060146,
"count": 233244,
"self": 4.649901537020469,
"children": {
"env_step": {
"total": 1819.3877503099466,
"count": 233244,
"self": 1535.7386053098821,
"children": {
"SubprocessEnvManager._take_step": {
"total": 280.9068467139783,
"count": 233244,
"self": 16.55717932198297,
"children": {
"TorchPolicy.evaluate": {
"total": 264.34966739199535,
"count": 222958,
"self": 264.34966739199535
}
}
},
"workers": {
"total": 2.742298286086225,
"count": 233244,
"self": 0.0,
"children": {
"worker_root": {
"total": 2360.0861006290397,
"count": 233244,
"is_parallel": true,
"self": 1108.178087601018,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008968580000328075,
"count": 1,
"is_parallel": true,
"self": 0.0002354040000227542,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006614540000100533,
"count": 2,
"is_parallel": true,
"self": 0.0006614540000100533
}
}
},
"UnityEnvironment.step": {
"total": 0.028658559000007244,
"count": 1,
"is_parallel": true,
"self": 0.00032734300003767203,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00021147100000007413,
"count": 1,
"is_parallel": true,
"self": 0.00021147100000007413
},
"communicator.exchange": {
"total": 0.027433772999984285,
"count": 1,
"is_parallel": true,
"self": 0.027433772999984285
},
"steps_from_proto": {
"total": 0.0006859719999852132,
"count": 1,
"is_parallel": true,
"self": 0.0001955320000206484,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0004904399999645648,
"count": 2,
"is_parallel": true,
"self": 0.0004904399999645648
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1251.9080130280217,
"count": 233243,
"is_parallel": true,
"self": 37.63544869406587,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 76.80489636596741,
"count": 233243,
"is_parallel": true,
"self": 76.80489636596741
},
"communicator.exchange": {
"total": 1049.3343032339362,
"count": 233243,
"is_parallel": true,
"self": 1049.3343032339362
},
"steps_from_proto": {
"total": 88.13336473405224,
"count": 233243,
"is_parallel": true,
"self": 33.20100289493547,
"children": {
"_process_rank_one_or_two_observation": {
"total": 54.932361839116766,
"count": 466486,
"is_parallel": true,
"self": 54.932361839116766
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 529.7809364590473,
"count": 233244,
"self": 6.296573907050515,
"children": {
"process_trajectory": {
"total": 147.3508507689952,
"count": 233244,
"self": 146.15512652399536,
"children": {
"RLTrainer._checkpoint": {
"total": 1.1957242449998375,
"count": 10,
"self": 1.1957242449998375
}
}
},
"_update_policy": {
"total": 376.13351178300167,
"count": 97,
"self": 316.5714839960079,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.56202778699378,
"count": 2910,
"self": 59.56202778699378
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.640004125481937e-07,
"count": 1,
"self": 8.640004125481937e-07
},
"TrainerController._save_models": {
"total": 0.12092666599983204,
"count": 1,
"self": 0.00199574099997335,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11893092499985869,
"count": 1,
"self": 0.11893092499985869
}
}
}
}
}
}
}