sd99's picture
First Push
15aa8aa
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0144290924072266,
"min": 1.0106556415557861,
"max": 2.8712525367736816,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9685.76953125,
"min": 9685.76953125,
"max": 29404.498046875,
"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": 12.31318187713623,
"min": 0.349673330783844,
"max": 12.31318187713623,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2401.070556640625,
"min": 67.83662414550781,
"max": 2472.32666015625,
"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": 0.06686948210378485,
"min": 0.06450966787159297,
"max": 0.07369698155540105,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2674779284151394,
"min": 0.2580386714863719,
"max": 0.35073670304001436,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2129016233717694,
"min": 0.10196041606375764,
"max": 0.2760243421091753,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8516064934870776,
"min": 0.40784166425503054,
"max": 1.3801217105458765,
"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": 24.181818181818183,
"min": 3.1136363636363638,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1064.0,
"min": 137.0,
"max": 1343.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.181818181818183,
"min": 3.1136363636363638,
"max": 24.418181818181818,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1064.0,
"min": 137.0,
"max": 1343.0,
"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": "1673593845",
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]",
"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": "1.21.6",
"end_time_seconds": "1673594311"
},
"total": 465.7848094389999,
"count": 1,
"self": 0.39247247200000857,
"children": {
"run_training.setup": {
"total": 0.12378649800007224,
"count": 1,
"self": 0.12378649800007224
},
"TrainerController.start_learning": {
"total": 465.2685504689998,
"count": 1,
"self": 0.5204186399437276,
"children": {
"TrainerController._reset_env": {
"total": 10.74757981799985,
"count": 1,
"self": 10.74757981799985
},
"TrainerController.advance": {
"total": 453.8621070830568,
"count": 18202,
"self": 0.27487964109513996,
"children": {
"env_step": {
"total": 453.58722744196166,
"count": 18202,
"self": 297.21449620096223,
"children": {
"SubprocessEnvManager._take_step": {
"total": 156.08793398499188,
"count": 18202,
"self": 1.4566137489796347,
"children": {
"TorchPolicy.evaluate": {
"total": 154.63132023601224,
"count": 18202,
"self": 34.16482560094687,
"children": {
"TorchPolicy.sample_actions": {
"total": 120.46649463506537,
"count": 18202,
"self": 120.46649463506537
}
}
}
}
},
"workers": {
"total": 0.28479725600755046,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 463.94114439796044,
"count": 18202,
"is_parallel": true,
"self": 226.43601482892586,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.009791347999907885,
"count": 1,
"is_parallel": true,
"self": 0.007075382999346402,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002715965000561482,
"count": 10,
"is_parallel": true,
"self": 0.002715965000561482
}
}
},
"UnityEnvironment.step": {
"total": 0.0520517159998235,
"count": 1,
"is_parallel": true,
"self": 0.00048587100013719464,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003038939998987189,
"count": 1,
"is_parallel": true,
"self": 0.0003038939998987189
},
"communicator.exchange": {
"total": 0.04957477899984042,
"count": 1,
"is_parallel": true,
"self": 0.04957477899984042
},
"steps_from_proto": {
"total": 0.001687171999947168,
"count": 1,
"is_parallel": true,
"self": 0.00042120699981751386,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001265965000129654,
"count": 10,
"is_parallel": true,
"self": 0.001265965000129654
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 237.50512956903458,
"count": 18201,
"is_parallel": true,
"self": 9.143872505971103,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.347119167028495,
"count": 18201,
"is_parallel": true,
"self": 5.347119167028495
},
"communicator.exchange": {
"total": 189.85265361802385,
"count": 18201,
"is_parallel": true,
"self": 189.85265361802385
},
"steps_from_proto": {
"total": 33.16148427801113,
"count": 18201,
"is_parallel": true,
"self": 7.109869768081808,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.051614509929323,
"count": 182010,
"is_parallel": true,
"self": 26.051614509929323
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.739899986816454e-05,
"count": 1,
"self": 4.739899986816454e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.5581363849335,
"count": 353476,
"is_parallel": true,
"self": 9.828921715978595,
"children": {
"process_trajectory": {
"total": 255.49115118895475,
"count": 353476,
"is_parallel": true,
"self": 254.68145591695543,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8096952719993169,
"count": 4,
"is_parallel": true,
"self": 0.8096952719993169
}
}
},
"_update_policy": {
"total": 185.23806348000016,
"count": 90,
"is_parallel": true,
"self": 48.3829256529682,
"children": {
"TorchPPOOptimizer.update": {
"total": 136.85513782703197,
"count": 4587,
"is_parallel": true,
"self": 136.85513782703197
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13839752899957602,
"count": 1,
"self": 0.0008600389992352575,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13753749000034077,
"count": 1,
"self": 0.13753749000034077
}
}
}
}
}
}
}