51nd0re1's picture
First Push
737903e verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8294293880462646,
"min": 0.8294293880462646,
"max": 2.8491976261138916,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7882.89697265625,
"min": 7882.89697265625,
"max": 29084.609375,
"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": 13.004318237304688,
"min": 0.4324893653392792,
"max": 13.004318237304688,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2535.842041015625,
"min": 83.90293884277344,
"max": 2637.892578125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06525117871719618,
"min": 0.06379232531612705,
"max": 0.07283118814150072,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26100471486878474,
"min": 0.2551693012645082,
"max": 0.36415594070750357,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18912466096819616,
"min": 0.13039121652642888,
"max": 0.2773517671169019,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7564986438727846,
"min": 0.5215648661057155,
"max": 1.3793100054357565,
"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": 25.40909090909091,
"min": 3.9545454545454546,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1118.0,
"min": 174.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.40909090909091,
"min": 3.9545454545454546,
"max": 25.863636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1118.0,
"min": 174.0,
"max": 1390.0,
"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": "1736215046",
"python_version": "3.10.12 (main, Nov 6 2024, 20:22:13) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./ml-agents/config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget.x86_64 --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": "2.5.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1736215468"
},
"total": 421.933266755,
"count": 1,
"self": 0.43769502100002455,
"children": {
"run_training.setup": {
"total": 0.056765449000010904,
"count": 1,
"self": 0.056765449000010904
},
"TrainerController.start_learning": {
"total": 421.43880628499994,
"count": 1,
"self": 0.34572365999349586,
"children": {
"TrainerController._reset_env": {
"total": 5.352076132999969,
"count": 1,
"self": 5.352076132999969
},
"TrainerController.advance": {
"total": 415.6562816790065,
"count": 18192,
"self": 0.3626147420077359,
"children": {
"env_step": {
"total": 292.89562077699924,
"count": 18192,
"self": 223.0254539240034,
"children": {
"SubprocessEnvManager._take_step": {
"total": 69.65870182499424,
"count": 18192,
"self": 1.2388717699990366,
"children": {
"TorchPolicy.evaluate": {
"total": 68.4198300549952,
"count": 18192,
"self": 68.4198300549952
}
}
},
"workers": {
"total": 0.21146502800161215,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 420.10682643499763,
"count": 18192,
"is_parallel": true,
"self": 224.85226252300373,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0020847570000341875,
"count": 1,
"is_parallel": true,
"self": 0.0006123980001007112,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014723589999334763,
"count": 10,
"is_parallel": true,
"self": 0.0014723589999334763
}
}
},
"UnityEnvironment.step": {
"total": 0.06937498399997821,
"count": 1,
"is_parallel": true,
"self": 0.0006366789999674438,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00037852299999485695,
"count": 1,
"is_parallel": true,
"self": 0.00037852299999485695
},
"communicator.exchange": {
"total": 0.06643650099999832,
"count": 1,
"is_parallel": true,
"self": 0.06643650099999832
},
"steps_from_proto": {
"total": 0.001923281000017596,
"count": 1,
"is_parallel": true,
"self": 0.0003612009999756083,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015620800000419877,
"count": 10,
"is_parallel": true,
"self": 0.0015620800000419877
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 195.2545639119939,
"count": 18191,
"is_parallel": true,
"self": 9.75321766601337,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.461456483994766,
"count": 18191,
"is_parallel": true,
"self": 5.461456483994766
},
"communicator.exchange": {
"total": 149.0328726589949,
"count": 18191,
"is_parallel": true,
"self": 149.0328726589949
},
"steps_from_proto": {
"total": 31.007017102990858,
"count": 18191,
"is_parallel": true,
"self": 5.5655000709885485,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.44151703200231,
"count": 181910,
"is_parallel": true,
"self": 25.44151703200231
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 122.39804615999952,
"count": 18192,
"self": 0.41860978300587703,
"children": {
"process_trajectory": {
"total": 27.666973403993723,
"count": 18192,
"self": 27.20222855399379,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4647448499999314,
"count": 4,
"self": 0.4647448499999314
}
}
},
"_update_policy": {
"total": 94.31246297299992,
"count": 90,
"self": 38.93530348500349,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.37715948799644,
"count": 4587,
"self": 55.37715948799644
}
}
}
}
}
}
},
"trainer_threads": {
"total": 8.91000013325538e-07,
"count": 1,
"self": 8.91000013325538e-07
},
"TrainerController._save_models": {
"total": 0.08472392199996648,
"count": 1,
"self": 0.0009598939999477807,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0837640280000187,
"count": 1,
"self": 0.0837640280000187
}
}
}
}
}
}
}