Laz4rz's picture
add Huggy agent
b888ae3 verified
{
"name": "root",
"gauges": {
"Huggy.Policy.Entropy.mean": {
"value": 1.4208875894546509,
"min": 1.4195122718811035,
"max": 1.428608775138855,
"count": 12
},
"Huggy.Policy.Entropy.sum": {
"value": 70318.3046875,
"min": 67531.9765625,
"max": 78362.7578125,
"count": 12
},
"Huggy.Environment.EpisodeLength.mean": {
"value": 101.45901639344262,
"min": 101.45901639344262,
"max": 418.19166666666666,
"count": 12
},
"Huggy.Environment.EpisodeLength.sum": {
"value": 49512.0,
"min": 49471.0,
"max": 50183.0,
"count": 12
},
"Huggy.Step.mean": {
"value": 599828.0,
"min": 49692.0,
"max": 599828.0,
"count": 12
},
"Huggy.Step.sum": {
"value": 599828.0,
"min": 49692.0,
"max": 599828.0,
"count": 12
},
"Huggy.Policy.ExtrinsicValueEstimate.mean": {
"value": 2.2470223903656006,
"min": 0.1304357349872589,
"max": 2.2470223903656006,
"count": 12
},
"Huggy.Policy.ExtrinsicValueEstimate.sum": {
"value": 1096.546875,
"min": 15.521852493286133,
"max": 1096.546875,
"count": 12
},
"Huggy.Environment.CumulativeReward.mean": {
"value": 3.844024112600772,
"min": 1.7325537450173323,
"max": 3.844024112600772,
"count": 12
},
"Huggy.Environment.CumulativeReward.sum": {
"value": 1875.8837669491768,
"min": 206.17389565706253,
"max": 1875.8837669491768,
"count": 12
},
"Huggy.Policy.ExtrinsicReward.mean": {
"value": 3.844024112600772,
"min": 1.7325537450173323,
"max": 3.844024112600772,
"count": 12
},
"Huggy.Policy.ExtrinsicReward.sum": {
"value": 1875.8837669491768,
"min": 206.17389565706253,
"max": 1875.8837669491768,
"count": 12
},
"Huggy.Losses.PolicyLoss.mean": {
"value": 0.015931323882088892,
"min": 0.015931323882088892,
"max": 0.01996262371055006,
"count": 12
},
"Huggy.Losses.PolicyLoss.sum": {
"value": 0.04779397164626668,
"min": 0.03193648516995987,
"max": 0.058428211135712144,
"count": 12
},
"Huggy.Losses.ValueLoss.mean": {
"value": 0.0450758658349514,
"min": 0.022682684908310574,
"max": 0.0450758658349514,
"count": 12
},
"Huggy.Losses.ValueLoss.sum": {
"value": 0.1352275975048542,
"min": 0.04536536981662115,
"max": 0.1352275975048542,
"count": 12
},
"Huggy.Policy.LearningRate.mean": {
"value": 0.00021354682881773334,
"min": 0.00021354682881773334,
"max": 0.000295284076571975,
"count": 12
},
"Huggy.Policy.LearningRate.sum": {
"value": 0.0006406404864532,
"min": 0.00044251640249454995,
"max": 0.00084421756859415,
"count": 12
},
"Huggy.Policy.Epsilon.mean": {
"value": 0.1711822666666667,
"min": 0.1711822666666667,
"max": 0.19842802500000004,
"count": 12
},
"Huggy.Policy.Epsilon.sum": {
"value": 0.5135468000000001,
"min": 0.34750545,
"max": 0.5814058499999999,
"count": 12
},
"Huggy.Policy.Beta.mean": {
"value": 0.003561995106666667,
"min": 0.003561995106666667,
"max": 0.0049215584475,
"count": 12
},
"Huggy.Policy.Beta.sum": {
"value": 0.01068598532,
"min": 0.007380521955000003,
"max": 0.014072151915,
"count": 12
},
"Huggy.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
},
"Huggy.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 12
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1714167266",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1714167974"
},
"total": 707.8142679609999,
"count": 1,
"self": 0.4645565099998521,
"children": {
"run_training.setup": {
"total": 0.05461420300002828,
"count": 1,
"self": 0.05461420300002828
},
"TrainerController.start_learning": {
"total": 707.295097248,
"count": 1,
"self": 1.229338077027478,
"children": {
"TrainerController._reset_env": {
"total": 3.0657460160000483,
"count": 1,
"self": 3.0657460160000483
},
"TrainerController.advance": {
"total": 702.6332968729723,
"count": 69336,
"self": 1.31836393800711,
"children": {
"env_step": {
"total": 561.5986178859772,
"count": 69336,
"self": 464.3156182549809,
"children": {
"SubprocessEnvManager._take_step": {
"total": 96.47588595803245,
"count": 69336,
"self": 5.327319449028323,
"children": {
"TorchPolicy.evaluate": {
"total": 91.14856650900413,
"count": 67506,
"self": 91.14856650900413
}
}
},
"workers": {
"total": 0.8071136729638511,
"count": 69335,
"self": 0.0,
"children": {
"worker_root": {
"total": 704.8895551749906,
"count": 69335,
"is_parallel": true,
"self": 328.67008184099757,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0008809470000414876,
"count": 1,
"is_parallel": true,
"self": 0.00020420499993178964,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.000676742000109698,
"count": 2,
"is_parallel": true,
"self": 0.000676742000109698
}
}
},
"UnityEnvironment.step": {
"total": 0.029428448000089702,
"count": 1,
"is_parallel": true,
"self": 0.0003741300000683623,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0002457870000398543,
"count": 1,
"is_parallel": true,
"self": 0.0002457870000398543
},
"communicator.exchange": {
"total": 0.028067412999916996,
"count": 1,
"is_parallel": true,
"self": 0.028067412999916996
},
"steps_from_proto": {
"total": 0.000741118000064489,
"count": 1,
"is_parallel": true,
"self": 0.0001928710001948275,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0005482469998696615,
"count": 2,
"is_parallel": true,
"self": 0.0005482469998696615
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 376.21947333399305,
"count": 69334,
"is_parallel": true,
"self": 11.604857663944586,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.28611157903481,
"count": 69334,
"is_parallel": true,
"self": 24.28611157903481
},
"communicator.exchange": {
"total": 313.4180416690109,
"count": 69334,
"is_parallel": true,
"self": 313.4180416690109
},
"steps_from_proto": {
"total": 26.91046242200275,
"count": 69334,
"is_parallel": true,
"self": 9.497006158012368,
"children": {
"_process_rank_one_or_two_observation": {
"total": 17.413456263990383,
"count": 138668,
"is_parallel": true,
"self": 17.413456263990383
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 139.716315048988,
"count": 69335,
"self": 1.9234566419544308,
"children": {
"process_trajectory": {
"total": 39.97038372403381,
"count": 69335,
"self": 39.525914113034105,
"children": {
"RLTrainer._checkpoint": {
"total": 0.44446961099970395,
"count": 3,
"self": 0.44446961099970395
}
}
},
"_update_policy": {
"total": 97.82247468299977,
"count": 29,
"self": 77.86595698099893,
"children": {
"TorchPPOOptimizer.update": {
"total": 19.956517702000838,
"count": 870,
"self": 19.956517702000838
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.45800004247576e-06,
"count": 1,
"self": 1.45800004247576e-06
},
"TrainerController._save_models": {
"total": 0.3667148240001552,
"count": 1,
"self": 0.008716064000282131,
"children": {
"RLTrainer._checkpoint": {
"total": 0.3579987599998731,
"count": 1,
"self": 0.3579987599998731
}
}
}
}
}
}
}