ppo-Huggy-1 / run_logs /timers.json
ScrappyCoco666's picture
initial version of Huggy
6a20748
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4036787748336792,
"min": 1.4036787748336792,
"max": 1.4300462007522583,
"count": 40
},
"Huggy.Policy.Entropy.sum": {
"value": 70787.5234375,
"min": 68327.7734375,
"max": 77909.0546875,
"count": 40
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 74.8907435508346,
"min": 68.66573816155989,
"max": 420.70588235294116,
"count": 40
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49353.0,
"min": 49224.0,
"max": 50064.0,
"count": 40
},
"Huggy.Step.mean": {
"value": 1999923.0,
"min": 49807.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Step.sum": {
"value": 1999923.0,
"min": 49807.0,
"max": 1999923.0,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.536053419113159,
"min": 0.13497397303581238,
"max": 2.5392391681671143,
"count": 40
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1671.25927734375,
"min": 15.926928520202637,
"max": 1789.396240234375,
"count": 40
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.9200233484255165,
"min": 1.974259465427722,
"max": 4.073511101553444,
"count": 40
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 2583.2953866124153,
"min": 232.9626169204712,
"max": 2822.754874765873,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.9200233484255165,
"min": 1.974259465427722,
"max": 4.073511101553444,
"count": 40
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 2583.2953866124153,
"min": 232.9626169204712,
"max": 2822.754874765873,
"count": 40
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.017910508696028653,
"min": 0.013506637646181239,
"max": 0.018919497128808874,
"count": 40
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.05373152608808596,
"min": 0.027013275292362478,
"max": 0.05614407776738517,
"count": 40
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.06136979286869367,
"min": 0.02126028494288524,
"max": 0.06647066852698723,
"count": 40
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.184109378606081,
"min": 0.04252056988577048,
"max": 0.184109378606081,
"count": 40
},
"Huggy.Policy.LearningRate.mean": {
"value": 4.038198653966678e-06,
"min": 4.038198653966678e-06,
"max": 0.000295322176559275,
"count": 40
},
"Huggy.Policy.LearningRate.sum": {
"value": 1.2114595961900033e-05,
"min": 1.2114595961900033e-05,
"max": 0.0008441563686145499,
"count": 40
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.10134603333333332,
"min": 0.10134603333333332,
"max": 0.19844072500000004,
"count": 40
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.3040381,
"min": 0.20782810000000002,
"max": 0.58138545,
"count": 40
},
"Huggy.Policy.Beta.mean": {
"value": 7.716706333333353e-05,
"min": 7.716706333333353e-05,
"max": 0.0049221921775,
"count": 40
},
"Huggy.Policy.Beta.sum": {
"value": 0.0002315011900000006,
"min": 0.0002315011900000006,
"max": 0.014071133955,
"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": "1670766023",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1670768450"
},
"total": 2427.666965864,
"count": 1,
"self": 0.38837506299978486,
"children": {
"run_training.setup": {
"total": 0.13201769900001636,
"count": 1,
"self": 0.13201769900001636
},
"TrainerController.start_learning": {
"total": 2427.146573102,
"count": 1,
"self": 4.330436089980594,
"children": {
"TrainerController._reset_env": {
"total": 10.194687378000026,
"count": 1,
"self": 10.194687378000026
},
"TrainerController.advance": {
"total": 2412.507426209019,
"count": 233454,
"self": 4.360820434088055,
"children": {
"env_step": {
"total": 1913.1862111279452,
"count": 233454,
"self": 1608.4224477079385,
"children": {
"SubprocessEnvManager._take_step": {
"total": 301.85487883590656,
"count": 233454,
"self": 15.730397311854404,
"children": {
"TorchPolicy.evaluate": {
"total": 286.12448152405216,
"count": 222945,
"self": 70.96037508604547,
"children": {
"TorchPolicy.sample_actions": {
"total": 215.16410643800668,
"count": 222945,
"self": 215.16410643800668
}
}
}
}
},
"workers": {
"total": 2.908884584100065,
"count": 233454,
"self": 0.0,
"children": {
"worker_root": {
"total": 2418.362847297053,
"count": 233454,
"is_parallel": true,
"self": 1096.6367096420195,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.001906256999973266,
"count": 1,
"is_parallel": true,
"self": 0.0003626430000167602,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015436139999565057,
"count": 2,
"is_parallel": true,
"self": 0.0015436139999565057
}
}
},
"UnityEnvironment.step": {
"total": 0.03113640599997325,
"count": 1,
"is_parallel": true,
"self": 0.0002868349998834674,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00019663400007630116,
"count": 1,
"is_parallel": true,
"self": 0.00019663400007630116
},
"communicator.exchange": {
"total": 0.029855071999918437,
"count": 1,
"is_parallel": true,
"self": 0.029855071999918437
},
"steps_from_proto": {
"total": 0.0007978650000950438,
"count": 1,
"is_parallel": true,
"self": 0.0002864560001398786,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005114089999551652,
"count": 2,
"is_parallel": true,
"self": 0.0005114089999551652
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1321.7261376550337,
"count": 233453,
"is_parallel": true,
"self": 37.556859720934426,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 87.71588460801775,
"count": 233453,
"is_parallel": true,
"self": 87.71588460801775
},
"communicator.exchange": {
"total": 1094.1884395480192,
"count": 233453,
"is_parallel": true,
"self": 1094.1884395480192
},
"steps_from_proto": {
"total": 102.26495377806202,
"count": 233453,
"is_parallel": true,
"self": 44.490150672928394,
"children": {
"_process_rank_one_or_two_observation": {
"total": 57.77480310513363,
"count": 466906,
"is_parallel": true,
"self": 57.77480310513363
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 494.9603946469857,
"count": 233454,
"self": 6.101093384892124,
"children": {
"process_trajectory": {
"total": 165.21080889309565,
"count": 233454,
"self": 164.70874806109532,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5020608320003248,
"count": 4,
"self": 0.5020608320003248
}
}
},
"_update_policy": {
"total": 323.64849236899795,
"count": 97,
"self": 269.77927636099685,
"children": {
"TorchPPOOptimizer.update": {
"total": 53.8692160080011,
"count": 2910,
"self": 53.8692160080011
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1490001270431094e-06,
"count": 1,
"self": 1.1490001270431094e-06
},
"TrainerController._save_models": {
"total": 0.11402227600001424,
"count": 1,
"self": 0.002025055000103748,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1119972209999105,
"count": 1,
"self": 0.1119972209999105
}
}
}
}
}
}
}