ppo-Huggy / run_logs /timers.json
jakobkruse's picture
Huggy training complete.
961373a
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.405090093612671,
"min": 1.405090093612671,
"max": 1.4289324283599854,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 69525.265625,
"min": 68010.9296875,
"max": 78619.15625,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 84.03577512776832,
"min": 79.11217948717949,
"max": 403.96774193548384,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49329.0,
"min": 49033.0,
"max": 50092.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999907.0,
"min": 49598.0,
"max": 1999907.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999907.0,
"min": 49598.0,
"max": 1999907.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.391476631164551,
"min": 0.16987638175487518,
"max": 2.4766411781311035,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1403.7967529296875,
"min": 20.894794464111328,
"max": 1499.5615234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.695313957521416,
"min": 1.7004048618359295,
"max": 3.927080886009168,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2169.149293065071,
"min": 209.14979800581932,
"max": 2293.3343920111656,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.695313957521416,
"min": 1.7004048618359295,
"max": 3.927080886009168,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2169.149293065071,
"min": 209.14979800581932,
"max": 2293.3343920111656,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017505447627303914,
"min": 0.013429393121865967,
"max": 0.02115772864490282,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.052516342881911746,
"min": 0.026858786243731933,
"max": 0.05899764289982462,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.05502296876576212,
"min": 0.0210005447268486,
"max": 0.05959873230506976,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.16506890629728635,
"min": 0.0420010894536972,
"max": 0.17757166201869645,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 3.6775487741833374e-06,
"min": 3.6775487741833374e-06,
"max": 0.00029533942655352496,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.1032646322550012e-05,
"min": 1.1032646322550012e-05,
"max": 0.0008442595685801497,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10122581666666668,
"min": 0.10122581666666668,
"max": 0.198446475,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.30367745,
"min": 0.20758210000000007,
"max": 0.58141985,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.116825166666675e-05,
"min": 7.116825166666675e-05,
"max": 0.0049224791025,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.00021350475500000026,
"min": 0.00021350475500000026,
"max": 0.014072850515000002,
"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": "1691407281",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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=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": "1691409897"
},
"total": 2616.5199046449998,
"count": 1,
"self": 0.43978352699969037,
"children": {
"run_training.setup": {
"total": 0.04334340200000497,
"count": 1,
"self": 0.04334340200000497
},
"TrainerController.start_learning": {
"total": 2616.036777716,
"count": 1,
"self": 5.069775352923898,
"children": {
"TrainerController._reset_env": {
"total": 5.443261560999986,
"count": 1,
"self": 5.443261560999986
},
"TrainerController.advance": {
"total": 2605.4015474780763,
"count": 232476,
"self": 5.049182813938387,
"children": {
"env_step": {
"total": 2034.9489135771116,
"count": 232476,
"self": 1718.1260014420445,
"children": {
"SubprocessEnvManager._take_step": {
"total": 313.53730335402304,
"count": 232476,
"self": 17.91534402006522,
"children": {
"TorchPolicy.evaluate": {
"total": 295.6219593339578,
"count": 222915,
"self": 295.6219593339578
}
}
},
"workers": {
"total": 3.2856087810440613,
"count": 232476,
"self": 0.0,
"children": {
"worker_root": {
"total": 2607.8245486619653,
"count": 232476,
"is_parallel": true,
"self": 1210.4823227280508,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0009463330000016867,
"count": 1,
"is_parallel": true,
"self": 0.00026795400003720715,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006783789999644796,
"count": 2,
"is_parallel": true,
"self": 0.0006783789999644796
}
}
},
"UnityEnvironment.step": {
"total": 0.0691779950000182,
"count": 1,
"is_parallel": true,
"self": 0.00036730599998691105,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002262360000031549,
"count": 1,
"is_parallel": true,
"self": 0.0002262360000031549
},
"communicator.exchange": {
"total": 0.0676803810000024,
"count": 1,
"is_parallel": true,
"self": 0.0676803810000024
},
"steps_from_proto": {
"total": 0.0009040720000257352,
"count": 1,
"is_parallel": true,
"self": 0.00025170500003923735,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0006523669999864978,
"count": 2,
"is_parallel": true,
"self": 0.0006523669999864978
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1397.3422259339145,
"count": 232475,
"is_parallel": true,
"self": 42.00756249588858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.75568311204711,
"count": 232475,
"is_parallel": true,
"self": 87.75568311204711
},
"communicator.exchange": {
"total": 1162.2155144650046,
"count": 232475,
"is_parallel": true,
"self": 1162.2155144650046
},
"steps_from_proto": {
"total": 105.3634658609742,
"count": 232475,
"is_parallel": true,
"self": 39.825901730053204,
"children": {
"_process_rank_one_or_two_observation": {
"total": 65.537564130921,
"count": 464950,
"is_parallel": true,
"self": 65.537564130921
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 565.403451087026,
"count": 232476,
"self": 7.4943393370598415,
"children": {
"process_trajectory": {
"total": 151.1714467669679,
"count": 232476,
"self": 149.89743132996904,
"children": {
"RLTrainer._checkpoint": {
"total": 1.2740154369988659,
"count": 10,
"self": 1.2740154369988659
}
}
},
"_update_policy": {
"total": 406.7376649829983,
"count": 97,
"self": 346.4079857909953,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.32967919200297,
"count": 2910,
"self": 60.32967919200297
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.870000212686136e-07,
"count": 1,
"self": 9.870000212686136e-07
},
"TrainerController._save_models": {
"total": 0.12219233699988763,
"count": 1,
"self": 0.0025815269996201096,
"children": {
"RLTrainer._checkpoint": {
"total": 0.11961081000026752,
"count": 1,
"self": 0.11961081000026752
}
}
}
}
}
}
}