AdanLee's picture
First training of SnowballTarget
60dac5c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7970032691955566,
"min": 0.7970032691955566,
"max": 2.8723626136779785,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7662.38916015625,
"min": 7662.38916015625,
"max": 29479.056640625,
"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": 12.835033416748047,
"min": 0.39278388023376465,
"max": 12.835033416748047,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2502.83154296875,
"min": 76.2000732421875,
"max": 2604.822509765625,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06608306042582233,
"min": 0.06392881739961298,
"max": 0.07725538416775903,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26433224170328934,
"min": 0.2557152695984519,
"max": 0.3862769208387951,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1893552669561377,
"min": 0.1190843652116646,
"max": 0.28175104131885603,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7574210678245508,
"min": 0.4763374608466584,
"max": 1.40875520659428,
"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": 24.954545454545453,
"min": 3.3863636363636362,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1098.0,
"min": 149.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.954545454545453,
"min": 3.3863636363636362,
"max": 25.318181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1098.0,
"min": 149.0,
"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": "1693277082",
"python_version": "3.10.12 (main, Jun 11 2023, 05:26:28) [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": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1693277555"
},
"total": 472.888091348,
"count": 1,
"self": 0.8527208460000111,
"children": {
"run_training.setup": {
"total": 0.06800976799991076,
"count": 1,
"self": 0.06800976799991076
},
"TrainerController.start_learning": {
"total": 471.96736073400007,
"count": 1,
"self": 0.5291267620062854,
"children": {
"TrainerController._reset_env": {
"total": 4.830773431000011,
"count": 1,
"self": 4.830773431000011
},
"TrainerController.advance": {
"total": 466.3772261109939,
"count": 18226,
"self": 0.2794594689930818,
"children": {
"env_step": {
"total": 466.0977666420008,
"count": 18226,
"self": 339.08716378700274,
"children": {
"SubprocessEnvManager._take_step": {
"total": 126.72921795099421,
"count": 18226,
"self": 1.8328005750036027,
"children": {
"TorchPolicy.evaluate": {
"total": 124.89641737599061,
"count": 18226,
"self": 124.89641737599061
}
}
},
"workers": {
"total": 0.2813849040038576,
"count": 18226,
"self": 0.0,
"children": {
"worker_root": {
"total": 470.447220309004,
"count": 18226,
"is_parallel": true,
"self": 225.04548200200293,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006845189000046048,
"count": 1,
"is_parallel": true,
"self": 0.004617965999955231,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022272230000908166,
"count": 10,
"is_parallel": true,
"self": 0.0022272230000908166
}
}
},
"UnityEnvironment.step": {
"total": 0.04738591699992867,
"count": 1,
"is_parallel": true,
"self": 0.0006277939999108639,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00030347699998856115,
"count": 1,
"is_parallel": true,
"self": 0.00030347699998856115
},
"communicator.exchange": {
"total": 0.04417145499996877,
"count": 1,
"is_parallel": true,
"self": 0.04417145499996877
},
"steps_from_proto": {
"total": 0.0022831910000604694,
"count": 1,
"is_parallel": true,
"self": 0.0004076580000855756,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018755329999748938,
"count": 10,
"is_parallel": true,
"self": 0.0018755329999748938
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 245.4017383070011,
"count": 18225,
"is_parallel": true,
"self": 10.459397699019974,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.23960465699804,
"count": 18225,
"is_parallel": true,
"self": 5.23960465699804
},
"communicator.exchange": {
"total": 194.17028596899445,
"count": 18225,
"is_parallel": true,
"self": 194.17028596899445
},
"steps_from_proto": {
"total": 35.532449981988634,
"count": 18225,
"is_parallel": true,
"self": 6.384398764010712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.148051217977923,
"count": 182250,
"is_parallel": true,
"self": 29.148051217977923
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.961599994312564e-05,
"count": 1,
"self": 9.961599994312564e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 462.88857613995503,
"count": 428136,
"is_parallel": true,
"self": 9.61084798293507,
"children": {
"process_trajectory": {
"total": 253.5302887890199,
"count": 428136,
"is_parallel": true,
"self": 251.88058005601988,
"children": {
"RLTrainer._checkpoint": {
"total": 1.6497087330000113,
"count": 4,
"is_parallel": true,
"self": 1.6497087330000113
}
}
},
"_update_policy": {
"total": 199.74743936800007,
"count": 90,
"is_parallel": true,
"self": 78.30011358500406,
"children": {
"TorchPPOOptimizer.update": {
"total": 121.44732578299602,
"count": 4587,
"is_parallel": true,
"self": 121.44732578299602
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23013481399993907,
"count": 1,
"self": 0.0012196899999707966,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22891512399996827,
"count": 1,
"self": 0.22891512399996827
}
}
}
}
}
}
}