12q3s's picture
First Push
42a0471 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8562203645706177,
"min": 0.8506782650947571,
"max": 2.8436012268066406,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8137.51806640625,
"min": 8137.51806640625,
"max": 29027.48046875,
"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": 13.062324523925781,
"min": 0.3562290668487549,
"max": 13.062324523925781,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2547.1533203125,
"min": 69.10843658447266,
"max": 2657.034912109375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07003565219734614,
"min": 0.05980153672292135,
"max": 0.07423279640546948,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2801426087893846,
"min": 0.2392061468916854,
"max": 0.3670115356586286,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.17880360701797055,
"min": 0.12299538485240191,
"max": 0.27555436404312356,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7152144280718822,
"min": 0.49198153940960765,
"max": 1.3777718202156177,
"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": 25.954545454545453,
"min": 3.6363636363636362,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1142.0,
"min": 160.0,
"max": 1410.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.954545454545453,
"min": 3.6363636363636362,
"max": 25.954545454545453,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1142.0,
"min": 160.0,
"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": "1742467319",
"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": "1742467776"
},
"total": 456.79858885,
"count": 1,
"self": 0.4390215820001231,
"children": {
"run_training.setup": {
"total": 0.024363323999978093,
"count": 1,
"self": 0.024363323999978093
},
"TrainerController.start_learning": {
"total": 456.3352039439999,
"count": 1,
"self": 0.4301899140050409,
"children": {
"TrainerController._reset_env": {
"total": 3.2231841190000523,
"count": 1,
"self": 3.2231841190000523
},
"TrainerController.advance": {
"total": 452.59049499299476,
"count": 18192,
"self": 0.43268139299971153,
"children": {
"env_step": {
"total": 324.4136915889858,
"count": 18192,
"self": 246.34626660599827,
"children": {
"SubprocessEnvManager._take_step": {
"total": 77.82441921400311,
"count": 18192,
"self": 1.4237618170091082,
"children": {
"TorchPolicy.evaluate": {
"total": 76.400657396994,
"count": 18192,
"self": 76.400657396994
}
}
},
"workers": {
"total": 0.2430057689844034,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.85350943800586,
"count": 18192,
"is_parallel": true,
"self": 239.06141082201418,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006686266999963664,
"count": 1,
"is_parallel": true,
"self": 0.005060589999857257,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001625677000106407,
"count": 10,
"is_parallel": true,
"self": 0.001625677000106407
}
}
},
"UnityEnvironment.step": {
"total": 0.044144198000026336,
"count": 1,
"is_parallel": true,
"self": 0.0006644630001346741,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004743829999824811,
"count": 1,
"is_parallel": true,
"self": 0.0004743829999824811
},
"communicator.exchange": {
"total": 0.040600455999992846,
"count": 1,
"is_parallel": true,
"self": 0.040600455999992846
},
"steps_from_proto": {
"total": 0.0024048959999163344,
"count": 1,
"is_parallel": true,
"self": 0.0004082919997472345,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0019966040001691,
"count": 10,
"is_parallel": true,
"self": 0.0019966040001691
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 215.79209861599168,
"count": 18191,
"is_parallel": true,
"self": 10.264848663981184,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.7472944829928565,
"count": 18191,
"is_parallel": true,
"self": 5.7472944829928565
},
"communicator.exchange": {
"total": 165.98193269599915,
"count": 18191,
"is_parallel": true,
"self": 165.98193269599915
},
"steps_from_proto": {
"total": 33.79802277301849,
"count": 18191,
"is_parallel": true,
"self": 6.208420113983152,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.589602659035336,
"count": 181910,
"is_parallel": true,
"self": 27.589602659035336
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 127.74412201100927,
"count": 18192,
"self": 0.5277690510320099,
"children": {
"process_trajectory": {
"total": 28.64721455697702,
"count": 18192,
"self": 28.181649513976936,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4655650430000833,
"count": 4,
"self": 0.4655650430000833
}
}
},
"_update_policy": {
"total": 98.56913840300024,
"count": 90,
"self": 39.36394412899904,
"children": {
"TorchPPOOptimizer.update": {
"total": 59.2051942740012,
"count": 4587,
"self": 59.2051942740012
}
}
}
}
}
}
},
"trainer_threads": {
"total": 7.900000582594657e-07,
"count": 1,
"self": 7.900000582594657e-07
},
"TrainerController._save_models": {
"total": 0.09133412799997132,
"count": 1,
"self": 0.0009668319999036612,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09036729600006765,
"count": 1,
"self": 0.09036729600006765
}
}
}
}
}
}
}