oukhan's picture
First Push
e6917a1 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.900183916091919,
"min": 0.900183916091919,
"max": 2.866269826889038,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8555.34765625,
"min": 8555.34765625,
"max": 29258.8828125,
"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": 13.07325267791748,
"min": 0.35041308403015137,
"max": 13.07325267791748,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2549.2841796875,
"min": 67.98014068603516,
"max": 2654.991943359375,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06397691995309787,
"min": 0.06216736964324453,
"max": 0.07231534019564267,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2559076798123915,
"min": 0.2559076798123915,
"max": 0.3608901072139441,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18782905043632378,
"min": 0.10758263925798053,
"max": 0.2767892395164453,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7513162017452951,
"min": 0.43033055703192213,
"max": 1.3839461975822265,
"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": 25.795454545454547,
"min": 3.1363636363636362,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1135.0,
"min": 138.0,
"max": 1413.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.795454545454547,
"min": 3.1363636363636362,
"max": 25.795454545454547,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1135.0,
"min": 138.0,
"max": 1413.0,
"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": "1769576435",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1769576993"
},
"total": 557.9218936220001,
"count": 1,
"self": 0.5373304900001585,
"children": {
"run_training.setup": {
"total": 0.04781699299996944,
"count": 1,
"self": 0.04781699299996944
},
"TrainerController.start_learning": {
"total": 557.336746139,
"count": 1,
"self": 0.6176218289959934,
"children": {
"TrainerController._reset_env": {
"total": 4.225879677999956,
"count": 1,
"self": 4.225879677999956
},
"TrainerController.advance": {
"total": 552.4212419880041,
"count": 18192,
"self": 0.5974842709894119,
"children": {
"env_step": {
"total": 395.75054461201137,
"count": 18192,
"self": 340.3496046170035,
"children": {
"SubprocessEnvManager._take_step": {
"total": 55.034604918001605,
"count": 18192,
"self": 1.7986326320000217,
"children": {
"TorchPolicy.evaluate": {
"total": 53.235972286001584,
"count": 18192,
"self": 53.235972286001584
}
}
},
"workers": {
"total": 0.3663350770062834,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 554.8077213060086,
"count": 18192,
"is_parallel": true,
"self": 259.6223092760072,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006836691999978939,
"count": 1,
"is_parallel": true,
"self": 0.004471434999913981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023652570000649575,
"count": 10,
"is_parallel": true,
"self": 0.0023652570000649575
}
}
},
"UnityEnvironment.step": {
"total": 0.05171236399996815,
"count": 1,
"is_parallel": true,
"self": 0.0006757980000884345,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004881199999999808,
"count": 1,
"is_parallel": true,
"self": 0.0004881199999999808
},
"communicator.exchange": {
"total": 0.04796273799991013,
"count": 1,
"is_parallel": true,
"self": 0.04796273799991013
},
"steps_from_proto": {
"total": 0.0025857079999695998,
"count": 1,
"is_parallel": true,
"self": 0.000441696000052616,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0021440119999169838,
"count": 10,
"is_parallel": true,
"self": 0.0021440119999169838
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 295.18541203000143,
"count": 18191,
"is_parallel": true,
"self": 13.280155968987174,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 7.135715064998976,
"count": 18191,
"is_parallel": true,
"self": 7.135715064998976
},
"communicator.exchange": {
"total": 228.8253541510103,
"count": 18191,
"is_parallel": true,
"self": 228.8253541510103
},
"steps_from_proto": {
"total": 45.94418684500499,
"count": 18191,
"is_parallel": true,
"self": 8.135904528962442,
"children": {
"_process_rank_one_or_two_observation": {
"total": 37.80828231604255,
"count": 181910,
"is_parallel": true,
"self": 37.80828231604255
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 156.07321310500333,
"count": 18192,
"self": 0.7674406940134304,
"children": {
"process_trajectory": {
"total": 28.64170400499063,
"count": 18192,
"self": 28.22487792499055,
"children": {
"RLTrainer._checkpoint": {
"total": 0.41682608000007804,
"count": 4,
"self": 0.41682608000007804
}
}
},
"_update_policy": {
"total": 126.66406840599927,
"count": 90,
"self": 47.15198421300033,
"children": {
"TorchPPOOptimizer.update": {
"total": 79.51208419299894,
"count": 4587,
"self": 79.51208419299894
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0159999419556698e-06,
"count": 1,
"self": 1.0159999419556698e-06
},
"TrainerController._save_models": {
"total": 0.07200162799995269,
"count": 1,
"self": 0.0009651579998717352,
"children": {
"RLTrainer._checkpoint": {
"total": 0.07103647000008095,
"count": 1,
"self": 0.07103647000008095
}
}
}
}
}
}
}