Nelsonlin0321's picture
First Push
4e51b78
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8645362257957458,
"min": 0.8645362257957458,
"max": 2.8556594848632812,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8254.591796875,
"min": 8254.591796875,
"max": 29433.28125,
"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": 12.923482894897461,
"min": 0.4903416335582733,
"max": 12.923482894897461,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2520.0791015625,
"min": 95.12627410888672,
"max": 2598.94091796875,
"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": 0.06854146731954339,
"min": 0.06311007110863084,
"max": 0.07451576683168099,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27416586927817355,
"min": 0.25343700336673586,
"max": 0.36760839040153753,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1832718495644775,
"min": 0.13411333305902742,
"max": 0.27500096588742495,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.73308739825791,
"min": 0.5364533322361097,
"max": 1.3750048294371249,
"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": 25.613636363636363,
"min": 3.5454545454545454,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1127.0,
"min": 156.0,
"max": 1381.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.613636363636363,
"min": 3.5454545454545454,
"max": 25.613636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1127.0,
"min": 156.0,
"max": 1381.0,
"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": "1678168426",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.22.4",
"end_time_seconds": "1678168914"
},
"total": 487.27787139,
"count": 1,
"self": 0.42397982699992554,
"children": {
"run_training.setup": {
"total": 0.12102162899998348,
"count": 1,
"self": 0.12102162899998348
},
"TrainerController.start_learning": {
"total": 486.73286993400006,
"count": 1,
"self": 0.6187413860036486,
"children": {
"TrainerController._reset_env": {
"total": 7.043018972000027,
"count": 1,
"self": 7.043018972000027
},
"TrainerController.advance": {
"total": 478.9428059479965,
"count": 18204,
"self": 0.31556965700099227,
"children": {
"env_step": {
"total": 478.6272362909955,
"count": 18204,
"self": 329.4511918130255,
"children": {
"SubprocessEnvManager._take_step": {
"total": 148.8741737169895,
"count": 18204,
"self": 1.806379774989523,
"children": {
"TorchPolicy.evaluate": {
"total": 147.06779394199998,
"count": 18204,
"self": 32.92740503798859,
"children": {
"TorchPolicy.sample_actions": {
"total": 114.14038890401139,
"count": 18204,
"self": 114.14038890401139
}
}
}
}
},
"workers": {
"total": 0.3018707609804778,
"count": 18204,
"self": 0.0,
"children": {
"worker_root": {
"total": 485.1185528029905,
"count": 18204,
"is_parallel": true,
"self": 233.31094240199093,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0022658660000161035,
"count": 1,
"is_parallel": true,
"self": 0.0008423660000289601,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014234999999871434,
"count": 10,
"is_parallel": true,
"self": 0.0014234999999871434
}
}
},
"UnityEnvironment.step": {
"total": 0.03700442399997428,
"count": 1,
"is_parallel": true,
"self": 0.0006010879999394092,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000306159000047046,
"count": 1,
"is_parallel": true,
"self": 0.000306159000047046
},
"communicator.exchange": {
"total": 0.034130604999973,
"count": 1,
"is_parallel": true,
"self": 0.034130604999973
},
"steps_from_proto": {
"total": 0.0019665720000148212,
"count": 1,
"is_parallel": true,
"self": 0.0004762810001466278,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014902909998681935,
"count": 10,
"is_parallel": true,
"self": 0.0014902909998681935
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 251.80761040099958,
"count": 18203,
"is_parallel": true,
"self": 9.871390067971447,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.6063701930056595,
"count": 18203,
"is_parallel": true,
"self": 5.6063701930056595
},
"communicator.exchange": {
"total": 202.5571999360111,
"count": 18203,
"is_parallel": true,
"self": 202.5571999360111
},
"steps_from_proto": {
"total": 33.77265020401137,
"count": 18203,
"is_parallel": true,
"self": 7.680546514032471,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.0921036899789,
"count": 182030,
"is_parallel": true,
"self": 26.0921036899789
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001279159998830437,
"count": 1,
"self": 0.0001279159998830437,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 475.1421621640761,
"count": 427538,
"is_parallel": true,
"self": 11.266920726130934,
"children": {
"process_trajectory": {
"total": 272.74615984694617,
"count": 427538,
"is_parallel": true,
"self": 271.3392403269462,
"children": {
"RLTrainer._checkpoint": {
"total": 1.406919519999974,
"count": 4,
"is_parallel": true,
"self": 1.406919519999974
}
}
},
"_update_policy": {
"total": 191.12908159099902,
"count": 90,
"is_parallel": true,
"self": 66.18166312400797,
"children": {
"TorchPPOOptimizer.update": {
"total": 124.94741846699105,
"count": 4587,
"is_parallel": true,
"self": 124.94741846699105
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.1281757120000293,
"count": 1,
"self": 0.0009180950000882149,
"children": {
"RLTrainer._checkpoint": {
"total": 0.1272576169999411,
"count": 1,
"self": 0.1272576169999411
}
}
}
}
}
}
}