MStarn's picture
First Push
4616add
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0178303718566895,
"min": 1.0178303718566895,
"max": 2.8613173961639404,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9718.244140625,
"min": 9718.244140625,
"max": 29334.2265625,
"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": 12.71945858001709,
"min": 0.41534778475761414,
"max": 12.71945858001709,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2480.29443359375,
"min": 80.57746887207031,
"max": 2552.3427734375,
"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": 0.07860872087093965,
"min": 0.06122145569088923,
"max": 0.07860872087093965,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3144348834837586,
"min": 0.258541216241771,
"max": 0.3666887946093601,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18077986548636477,
"min": 0.11071953695842668,
"max": 0.2563749147104282,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7231194619454591,
"min": 0.4428781478337067,
"max": 1.2753982643286388,
"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": 25.886363636363637,
"min": 3.2954545454545454,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1139.0,
"min": 145.0,
"max": 1375.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.886363636363637,
"min": 3.2954545454545454,
"max": 25.886363636363637,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1139.0,
"min": 145.0,
"max": 1375.0,
"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": "1695610114",
"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": "1695610714"
},
"total": 600.0628794319999,
"count": 1,
"self": 0.48687169700008326,
"children": {
"run_training.setup": {
"total": 0.07765042099993025,
"count": 1,
"self": 0.07765042099993025
},
"TrainerController.start_learning": {
"total": 599.4983573139999,
"count": 1,
"self": 0.7627626030102874,
"children": {
"TrainerController._reset_env": {
"total": 5.071006262999958,
"count": 1,
"self": 5.071006262999958
},
"TrainerController.advance": {
"total": 593.4960019309897,
"count": 18200,
"self": 0.39523767200114435,
"children": {
"env_step": {
"total": 593.1007642589885,
"count": 18200,
"self": 435.3421928609582,
"children": {
"SubprocessEnvManager._take_step": {
"total": 157.3636837720145,
"count": 18200,
"self": 2.2834955699939883,
"children": {
"TorchPolicy.evaluate": {
"total": 155.0801882020205,
"count": 18200,
"self": 155.0801882020205
}
}
},
"workers": {
"total": 0.39488762601581584,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 597.3515355559937,
"count": 18200,
"is_parallel": true,
"self": 277.0661588370016,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00768569199999547,
"count": 1,
"is_parallel": true,
"self": 0.004717423999977655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002968268000017815,
"count": 10,
"is_parallel": true,
"self": 0.002968268000017815
}
}
},
"UnityEnvironment.step": {
"total": 0.042742684000018016,
"count": 1,
"is_parallel": true,
"self": 0.0007126220001509864,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003962319999573083,
"count": 1,
"is_parallel": true,
"self": 0.0003962319999573083
},
"communicator.exchange": {
"total": 0.037995561000002454,
"count": 1,
"is_parallel": true,
"self": 0.037995561000002454
},
"steps_from_proto": {
"total": 0.003638268999907268,
"count": 1,
"is_parallel": true,
"self": 0.000456904999850849,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.003181364000056419,
"count": 10,
"is_parallel": true,
"self": 0.003181364000056419
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 320.2853767189921,
"count": 18199,
"is_parallel": true,
"self": 13.362487333960985,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.811097406005615,
"count": 18199,
"is_parallel": true,
"self": 6.811097406005615
},
"communicator.exchange": {
"total": 251.49113239501798,
"count": 18199,
"is_parallel": true,
"self": 251.49113239501798
},
"steps_from_proto": {
"total": 48.62065958400751,
"count": 18199,
"is_parallel": true,
"self": 9.41572022903074,
"children": {
"_process_rank_one_or_two_observation": {
"total": 39.20493935497677,
"count": 181990,
"is_parallel": true,
"self": 39.20493935497677
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.674100000556791e-05,
"count": 1,
"self": 4.674100000556791e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 588.1130241940568,
"count": 565516,
"is_parallel": true,
"self": 14.202436979101776,
"children": {
"process_trajectory": {
"total": 325.0578126979548,
"count": 565516,
"is_parallel": true,
"self": 322.87297302695504,
"children": {
"RLTrainer._checkpoint": {
"total": 2.184839670999736,
"count": 4,
"is_parallel": true,
"self": 2.184839670999736
}
}
},
"_update_policy": {
"total": 248.85277451700028,
"count": 90,
"is_parallel": true,
"self": 102.41726998699869,
"children": {
"TorchPPOOptimizer.update": {
"total": 146.4355045300016,
"count": 4587,
"is_parallel": true,
"self": 146.4355045300016
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1685397759999887,
"count": 1,
"self": 0.0009215630000198871,
"children": {
"RLTrainer._checkpoint": {
"total": 0.16761821299996882,
"count": 1,
"self": 0.16761821299996882
}
}
}
}
}
}
}