ange0102's picture
First Push
b422655
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9334625005722046,
"min": 0.9334625005722046,
"max": 2.864825963973999,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8922.9677734375,
"min": 8922.9677734375,
"max": 29401.708984375,
"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": 13.20810317993164,
"min": 0.4937330484390259,
"max": 13.20810317993164,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2575.580078125,
"min": 95.78421020507812,
"max": 2693.66748046875,
"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.Losses.PolicyLoss.mean": {
"value": 0.07029364521847181,
"min": 0.06423030557754614,
"max": 0.07649387423432427,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28117458087388725,
"min": 0.25692122231018455,
"max": 0.35988773940377594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1959452915425394,
"min": 0.1586867324932588,
"max": 0.28479515702701086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7837811661701576,
"min": 0.6347469299730352,
"max": 1.3642610963068758,
"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": 26.113636363636363,
"min": 4.340909090909091,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1149.0,
"min": 191.0,
"max": 1422.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 26.113636363636363,
"min": 4.340909090909091,
"max": 26.113636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1149.0,
"min": 191.0,
"max": 1422.0,
"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": "1692100026",
"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": "1692100532"
},
"total": 505.89813634100005,
"count": 1,
"self": 0.7927370390001443,
"children": {
"run_training.setup": {
"total": 0.06636567900000045,
"count": 1,
"self": 0.06636567900000045
},
"TrainerController.start_learning": {
"total": 505.0390336229999,
"count": 1,
"self": 0.6187357679984871,
"children": {
"TrainerController._reset_env": {
"total": 4.888396467000007,
"count": 1,
"self": 4.888396467000007
},
"TrainerController.advance": {
"total": 499.30140636200167,
"count": 18214,
"self": 0.29678329500734435,
"children": {
"env_step": {
"total": 499.0046230669943,
"count": 18214,
"self": 366.27008331900197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 132.42285767799012,
"count": 18214,
"self": 2.063992792988074,
"children": {
"TorchPolicy.evaluate": {
"total": 130.35886488500205,
"count": 18214,
"self": 130.35886488500205
}
}
},
"workers": {
"total": 0.31168207000223447,
"count": 18214,
"self": 0.0,
"children": {
"worker_root": {
"total": 502.9880310220085,
"count": 18214,
"is_parallel": true,
"self": 238.89427327601368,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006015044999912789,
"count": 1,
"is_parallel": true,
"self": 0.004417523999904915,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015975210000078732,
"count": 10,
"is_parallel": true,
"self": 0.0015975210000078732
}
}
},
"UnityEnvironment.step": {
"total": 0.06646300099998825,
"count": 1,
"is_parallel": true,
"self": 0.0007784260001244547,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000495315999955892,
"count": 1,
"is_parallel": true,
"self": 0.000495315999955892
},
"communicator.exchange": {
"total": 0.062347370999987106,
"count": 1,
"is_parallel": true,
"self": 0.062347370999987106
},
"steps_from_proto": {
"total": 0.0028418879999208,
"count": 1,
"is_parallel": true,
"self": 0.0005871319998504987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0022547560000703015,
"count": 10,
"is_parallel": true,
"self": 0.0022547560000703015
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 264.0937577459948,
"count": 18213,
"is_parallel": true,
"self": 11.073081524019017,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.584788920975711,
"count": 18213,
"is_parallel": true,
"self": 5.584788920975711
},
"communicator.exchange": {
"total": 208.71726189200888,
"count": 18213,
"is_parallel": true,
"self": 208.71726189200888
},
"steps_from_proto": {
"total": 38.718625408991215,
"count": 18213,
"is_parallel": true,
"self": 7.1293288969654895,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.589296512025726,
"count": 182130,
"is_parallel": true,
"self": 31.589296512025726
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00017772699993656715,
"count": 1,
"self": 0.00017772699993656715,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 495.369225218922,
"count": 469234,
"is_parallel": true,
"self": 10.977965783938544,
"children": {
"process_trajectory": {
"total": 272.86276201498345,
"count": 469234,
"is_parallel": true,
"self": 271.09525279198374,
"children": {
"RLTrainer._checkpoint": {
"total": 1.7675092229997063,
"count": 4,
"is_parallel": true,
"self": 1.7675092229997063
}
}
},
"_update_policy": {
"total": 211.52849742,
"count": 90,
"is_parallel": true,
"self": 85.48087314100371,
"children": {
"TorchPPOOptimizer.update": {
"total": 126.0476242789963,
"count": 4584,
"is_parallel": true,
"self": 126.0476242789963
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.23031729899980746,
"count": 1,
"self": 0.0012100629996893986,
"children": {
"RLTrainer._checkpoint": {
"total": 0.22910723600011806,
"count": 1,
"self": 0.22910723600011806
}
}
}
}
}
}
}