Facepalm0's picture
First Push
4ce92c9 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7936244010925293,
"min": 0.7936244010925293,
"max": 2.8679563999176025,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7577.52587890625,
"min": 7577.52587890625,
"max": 29370.7421875,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.103399276733398,
"min": 0.33422356843948364,
"max": 13.103399276733398,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2555.162841796875,
"min": 64.83937072753906,
"max": 2646.64892578125,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07154081474622145,
"min": 0.06064616564168211,
"max": 0.07769435846678201,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2861632589848858,
"min": 0.2578170460494185,
"max": 0.36296957858219536,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18753617264184297,
"min": 0.11357172366857127,
"max": 0.276449315162266,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7501446905673719,
"min": 0.45428689467428507,
"max": 1.38224657581133,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.568181818181817,
"min": 3.227272727272727,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1125.0,
"min": 142.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.568181818181817,
"min": 3.227272727272727,
"max": 25.772727272727273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1125.0,
"min": 142.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1707035698",
"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/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707036148"
},
"total": 449.95280335300004,
"count": 1,
"self": 0.5004762840000012,
"children": {
"run_training.setup": {
"total": 0.0519325980000076,
"count": 1,
"self": 0.0519325980000076
},
"TrainerController.start_learning": {
"total": 449.400394471,
"count": 1,
"self": 0.6090100889887253,
"children": {
"TrainerController._reset_env": {
"total": 3.255812523999907,
"count": 1,
"self": 3.255812523999907
},
"TrainerController.advance": {
"total": 445.4304646280117,
"count": 18199,
"self": 0.27165335501149457,
"children": {
"env_step": {
"total": 445.1588112730002,
"count": 18199,
"self": 288.6761418959718,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.19755697900735,
"count": 18199,
"self": 1.4589572420032937,
"children": {
"TorchPolicy.evaluate": {
"total": 154.73859973700405,
"count": 18199,
"self": 154.73859973700405
}
}
},
"workers": {
"total": 0.2851123980210559,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 448.107882063995,
"count": 18199,
"is_parallel": true,
"self": 220.34801599698574,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005171806000021206,
"count": 1,
"is_parallel": true,
"self": 0.003472909999914009,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016988960001071973,
"count": 10,
"is_parallel": true,
"self": 0.0016988960001071973
}
}
},
"UnityEnvironment.step": {
"total": 0.03844043200001579,
"count": 1,
"is_parallel": true,
"self": 0.0007063539999307977,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004244620000690702,
"count": 1,
"is_parallel": true,
"self": 0.0004244620000690702
},
"communicator.exchange": {
"total": 0.03530788800003393,
"count": 1,
"is_parallel": true,
"self": 0.03530788800003393
},
"steps_from_proto": {
"total": 0.002001727999981995,
"count": 1,
"is_parallel": true,
"self": 0.0004052200000614903,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015965079999205045,
"count": 10,
"is_parallel": true,
"self": 0.0015965079999205045
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.75986606700928,
"count": 18198,
"is_parallel": true,
"self": 10.987924539059918,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.422644935981339,
"count": 18198,
"is_parallel": true,
"self": 5.422644935981339
},
"communicator.exchange": {
"total": 177.076454390982,
"count": 18198,
"is_parallel": true,
"self": 177.076454390982
},
"steps_from_proto": {
"total": 34.27284220098602,
"count": 18198,
"is_parallel": true,
"self": 6.388323114951845,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.884519086034175,
"count": 181980,
"is_parallel": true,
"self": 27.884519086034175
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001315109998358821,
"count": 1,
"self": 0.0001315109998358821,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 439.6625806739876,
"count": 689428,
"is_parallel": true,
"self": 15.060976565991268,
"children": {
"process_trajectory": {
"total": 240.88324141899727,
"count": 689428,
"is_parallel": true,
"self": 240.3471324459971,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5361089730001822,
"count": 4,
"is_parallel": true,
"self": 0.5361089730001822
}
}
},
"_update_policy": {
"total": 183.71836268899904,
"count": 90,
"is_parallel": true,
"self": 52.91391553999756,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.80444714900148,
"count": 4587,
"is_parallel": true,
"self": 130.80444714900148
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.10497571899986724,
"count": 1,
"self": 0.0010318319998532388,
"children": {
"RLTrainer._checkpoint": {
"total": 0.103943887000014,
"count": 1,
"self": 0.103943887000014
}
}
}
}
}
}
}