trannhoduc's picture
First Push
9c0168b verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 2.126556396484375,
"min": 2.126556396484375,
"max": 2.8353991508483887,
"count": 5
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 21707.88671875,
"min": 21707.88671875,
"max": 28943.75390625,
"count": 5
},
"SnowballTarget.Step.mean": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Step.sum": {
"value": 49936.0,
"min": 9952.0,
"max": 49936.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 5.055191993713379,
"min": 0.49142876267433167,
"max": 5.055191993713379,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 980.707275390625,
"min": 95.3371810913086,
"max": 980.707275390625,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06882511875615,
"min": 0.06434970744068742,
"max": 0.0748176361005023,
"count": 5
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2753004750246,
"min": 0.2573988297627497,
"max": 0.37408818050251147,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.25498449269170853,
"min": 0.12248344919370377,
"max": 0.280079622552091,
"count": 5
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.0199379707668341,
"min": 0.4899337967748151,
"max": 1.3042290093852025,
"count": 5
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 2.9928090024000003e-05,
"min": 2.9928090024000003e-05,
"max": 0.00026752801082399996,
"count": 5
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 0.00011971236009600001,
"min": 0.00011971236009600001,
"max": 0.0010701120432959998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10997600000000002,
"min": 0.10997600000000002,
"max": 0.18917599999999998,
"count": 5
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.4399040000000001,
"min": 0.4399040000000001,
"max": 0.8468800000000001,
"count": 5
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0005078024,
"min": 0.0005078024,
"max": 0.0044598824,
"count": 5
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0020312096,
"min": 0.0020312096,
"max": 0.0178395296,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 5
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 12.045454545454545,
"min": 3.659090909090909,
"max": 12.045454545454545,
"count": 5
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 530.0,
"min": 161.0,
"max": 646.0,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 12.045454545454545,
"min": 3.659090909090909,
"max": 12.045454545454545,
"count": 5
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 530.0,
"min": 161.0,
"max": 646.0,
"count": 5
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 5
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1751279787",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1751279904"
},
"total": 116.44097150100015,
"count": 1,
"self": 0.4319538200002171,
"children": {
"run_training.setup": {
"total": 0.023217351999960556,
"count": 1,
"self": 0.023217351999960556
},
"TrainerController.start_learning": {
"total": 115.98580032899997,
"count": 1,
"self": 0.10956149700018614,
"children": {
"TrainerController._reset_env": {
"total": 3.0811590499999966,
"count": 1,
"self": 3.0811590499999966
},
"TrainerController.advance": {
"total": 112.70619872899977,
"count": 4592,
"self": 0.11497461599924463,
"children": {
"env_step": {
"total": 81.71157938300087,
"count": 4592,
"self": 62.72419470999205,
"children": {
"SubprocessEnvManager._take_step": {
"total": 18.920794615001796,
"count": 4592,
"self": 0.3422426959961058,
"children": {
"TorchPolicy.evaluate": {
"total": 18.57855191900569,
"count": 4592,
"self": 18.57855191900569
}
}
},
"workers": {
"total": 0.06659005800702289,
"count": 4592,
"self": 0.0,
"children": {
"worker_root": {
"total": 115.43692099800091,
"count": 4592,
"is_parallel": true,
"self": 60.74889574200074,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005220903000008548,
"count": 1,
"is_parallel": true,
"self": 0.0037807080000220594,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014401949999864883,
"count": 10,
"is_parallel": true,
"self": 0.0014401949999864883
}
}
},
"UnityEnvironment.step": {
"total": 0.04348885899992183,
"count": 1,
"is_parallel": true,
"self": 0.0006531090000407858,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005680529999381179,
"count": 1,
"is_parallel": true,
"self": 0.0005680529999381179
},
"communicator.exchange": {
"total": 0.04016853199993875,
"count": 1,
"is_parallel": true,
"self": 0.04016853199993875
},
"steps_from_proto": {
"total": 0.0020991650000041773,
"count": 1,
"is_parallel": true,
"self": 0.00037755199991806876,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017216130000861085,
"count": 10,
"is_parallel": true,
"self": 0.0017216130000861085
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 54.688025256000174,
"count": 4591,
"is_parallel": true,
"self": 2.547232643010034,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 1.4401503609956308,
"count": 4591,
"is_parallel": true,
"self": 1.4401503609956308
},
"communicator.exchange": {
"total": 42.258823283996776,
"count": 4591,
"is_parallel": true,
"self": 42.258823283996776
},
"steps_from_proto": {
"total": 8.441818967997733,
"count": 4591,
"is_parallel": true,
"self": 1.5502447339812306,
"children": {
"_process_rank_one_or_two_observation": {
"total": 6.8915742340165025,
"count": 45910,
"is_parallel": true,
"self": 6.8915742340165025
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 30.879644729999654,
"count": 4592,
"self": 0.14296713300279862,
"children": {
"process_trajectory": {
"total": 7.713917545996992,
"count": 4592,
"self": 6.773118224996892,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9407993210000996,
"count": 10,
"self": 0.9407993210000996
}
}
},
"_update_policy": {
"total": 23.022760050999864,
"count": 22,
"self": 9.28723621699885,
"children": {
"TorchPPOOptimizer.update": {
"total": 13.735523834001015,
"count": 1119,
"self": 13.735523834001015
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.860000318440143e-07,
"count": 1,
"self": 9.860000318440143e-07
},
"TrainerController._save_models": {
"total": 0.08888006699999096,
"count": 1,
"self": 0.0008628880000287609,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0880171789999622,
"count": 1,
"self": 0.0880171789999622
}
}
}
}
}
}
}