wflying's picture
First Push
28e206a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.062557339668274,
"min": 1.062557339668274,
"max": 2.8550302982330322,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10098.544921875,
"min": 10098.544921875,
"max": 29144.1484375,
"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": 12.113380432128906,
"min": 0.43743467330932617,
"max": 12.113380432128906,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2362.109130859375,
"min": 84.8623275756836,
"max": 2435.79345703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07193702216503808,
"min": 0.06097958867979412,
"max": 0.07483818515559988,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28774808866015233,
"min": 0.24391835471917647,
"max": 0.3554919485993428,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20842781546069128,
"min": 0.13611026061698794,
"max": 0.2768260792189953,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8337112618427651,
"min": 0.5444410424679518,
"max": 1.3841303960949767,
"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.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.Environment.CumulativeReward.mean": {
"value": 24.15909090909091,
"min": 3.409090909090909,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1063.0,
"min": 150.0,
"max": 1301.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.15909090909091,
"min": 3.409090909090909,
"max": 24.15909090909091,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1063.0,
"min": 150.0,
"max": 1301.0,
"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": "1738977967",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1738978406"
},
"total": 439.12376278500005,
"count": 1,
"self": 0.43322722699997485,
"children": {
"run_training.setup": {
"total": 0.02302388400005384,
"count": 1,
"self": 0.02302388400005384
},
"TrainerController.start_learning": {
"total": 438.667511674,
"count": 1,
"self": 0.37865475198884724,
"children": {
"TrainerController._reset_env": {
"total": 2.850213634999932,
"count": 1,
"self": 2.850213634999932
},
"TrainerController.advance": {
"total": 435.34865399201135,
"count": 18192,
"self": 0.38570107701298184,
"children": {
"env_step": {
"total": 309.7506420190027,
"count": 18192,
"self": 234.40972331401713,
"children": {
"SubprocessEnvManager._take_step": {
"total": 75.12096318499698,
"count": 18192,
"self": 1.3266180949925683,
"children": {
"TorchPolicy.evaluate": {
"total": 73.79434509000441,
"count": 18192,
"self": 73.79434509000441
}
}
},
"workers": {
"total": 0.2199555199886163,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 437.1817282900007,
"count": 18192,
"is_parallel": true,
"self": 232.0816690749915,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0053222719999439505,
"count": 1,
"is_parallel": true,
"self": 0.0038045919999376565,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001517680000006294,
"count": 10,
"is_parallel": true,
"self": 0.001517680000006294
}
}
},
"UnityEnvironment.step": {
"total": 0.0368056309999929,
"count": 1,
"is_parallel": true,
"self": 0.0006161390001580003,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003664500000013504,
"count": 1,
"is_parallel": true,
"self": 0.0003664500000013504
},
"communicator.exchange": {
"total": 0.033965368999929524,
"count": 1,
"is_parallel": true,
"self": 0.033965368999929524
},
"steps_from_proto": {
"total": 0.0018576729999040253,
"count": 1,
"is_parallel": true,
"self": 0.0003642990000116697,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014933739998923556,
"count": 10,
"is_parallel": true,
"self": 0.0014933739998923556
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 205.1000592150092,
"count": 18191,
"is_parallel": true,
"self": 9.834486554032082,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.338556760002575,
"count": 18191,
"is_parallel": true,
"self": 5.338556760002575
},
"communicator.exchange": {
"total": 157.7740536739799,
"count": 18191,
"is_parallel": true,
"self": 157.7740536739799
},
"steps_from_proto": {
"total": 32.152962226994646,
"count": 18191,
"is_parallel": true,
"self": 5.75912587996504,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.393836347029605,
"count": 181910,
"is_parallel": true,
"self": 26.393836347029605
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.21231089599564,
"count": 18192,
"self": 0.4705389419821131,
"children": {
"process_trajectory": {
"total": 27.637044248013012,
"count": 18192,
"self": 26.980230920013014,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6568133279999984,
"count": 4,
"self": 0.6568133279999984
}
}
},
"_update_policy": {
"total": 97.10472770600052,
"count": 90,
"self": 38.954944911003736,
"children": {
"TorchPPOOptimizer.update": {
"total": 58.14978279499678,
"count": 4587,
"self": 58.14978279499678
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.020000106829684e-07,
"count": 1,
"self": 9.020000106829684e-07
},
"TrainerController._save_models": {
"total": 0.08998839299988504,
"count": 1,
"self": 0.000955866999902355,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08903252599998268,
"count": 1,
"self": 0.08903252599998268
}
}
}
}
}
}
}