huanvo88's picture
Initial Model
9b204d1
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9881963729858398,
"min": 0.9881963729858398,
"max": 2.8701257705688477,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9435.298828125,
"min": 9435.298828125,
"max": 29456.1015625,
"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": 12.759928703308105,
"min": 0.373454213142395,
"max": 12.759928703308105,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2488.18603515625,
"min": 72.45011901855469,
"max": 2586.25390625,
"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": 0.06204611359520213,
"min": 0.06204611359520213,
"max": 0.07735631403458469,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.24818445438080852,
"min": 0.24818445438080852,
"max": 0.3867815701729235,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2260681924720605,
"min": 0.1342646095846944,
"max": 0.300543942696908,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.904272769888242,
"min": 0.5370584383387776,
"max": 1.5027197134845398,
"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": 24.454545454545453,
"min": 3.659090909090909,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1076.0,
"min": 161.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.454545454545453,
"min": 3.659090909090909,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1076.0,
"min": 161.0,
"max": 1388.0,
"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": "1684326152",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [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": "0.31.0.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": "1684326613"
},
"total": 460.68780505000007,
"count": 1,
"self": 0.7518330740000465,
"children": {
"run_training.setup": {
"total": 0.041492692000019815,
"count": 1,
"self": 0.041492692000019815
},
"TrainerController.start_learning": {
"total": 459.894479284,
"count": 1,
"self": 0.5356073499842751,
"children": {
"TrainerController._reset_env": {
"total": 4.910791700000004,
"count": 1,
"self": 4.910791700000004
},
"TrainerController.advance": {
"total": 454.2376209970158,
"count": 18215,
"self": 0.2556085080042294,
"children": {
"env_step": {
"total": 453.9820124890116,
"count": 18215,
"self": 332.4316694890082,
"children": {
"SubprocessEnvManager._take_step": {
"total": 121.29731958299851,
"count": 18215,
"self": 1.75438532098633,
"children": {
"TorchPolicy.evaluate": {
"total": 119.54293426201218,
"count": 18215,
"self": 119.54293426201218
}
}
},
"workers": {
"total": 0.25302341700489706,
"count": 18215,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.2191535099944,
"count": 18215,
"is_parallel": true,
"self": 217.20182069296868,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005165629000089211,
"count": 1,
"is_parallel": true,
"self": 0.0035876300001973505,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015779989998918609,
"count": 10,
"is_parallel": true,
"self": 0.0015779989998918609
}
}
},
"UnityEnvironment.step": {
"total": 0.06770502499989561,
"count": 1,
"is_parallel": true,
"self": 0.0007185109999454653,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004269769999609707,
"count": 1,
"is_parallel": true,
"self": 0.0004269769999609707
},
"communicator.exchange": {
"total": 0.06383361700000023,
"count": 1,
"is_parallel": true,
"self": 0.06383361700000023
},
"steps_from_proto": {
"total": 0.002725919999988946,
"count": 1,
"is_parallel": true,
"self": 0.000551579999751084,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002174340000237862,
"count": 10,
"is_parallel": true,
"self": 0.002174340000237862
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 241.0173328170257,
"count": 18214,
"is_parallel": true,
"self": 9.798470512996232,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.239000447024068,
"count": 18214,
"is_parallel": true,
"self": 5.239000447024068
},
"communicator.exchange": {
"total": 193.2702510600103,
"count": 18214,
"is_parallel": true,
"self": 193.2702510600103
},
"steps_from_proto": {
"total": 32.70961079699509,
"count": 18214,
"is_parallel": true,
"self": 6.246956029966327,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.462654767028766,
"count": 182140,
"is_parallel": true,
"self": 26.462654767028766
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00013125400005264964,
"count": 1,
"self": 0.00013125400005264964,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 450.74987893304944,
"count": 427890,
"is_parallel": true,
"self": 9.583201061016553,
"children": {
"process_trajectory": {
"total": 245.65549735803404,
"count": 427890,
"is_parallel": true,
"self": 244.15327291003393,
"children": {
"RLTrainer._checkpoint": {
"total": 1.5022244480001063,
"count": 4,
"is_parallel": true,
"self": 1.5022244480001063
}
}
},
"_update_policy": {
"total": 195.51118051399885,
"count": 90,
"is_parallel": true,
"self": 74.85998048099111,
"children": {
"TorchPPOOptimizer.update": {
"total": 120.65120003300774,
"count": 4587,
"is_parallel": true,
"self": 120.65120003300774
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.2103279829998428,
"count": 1,
"self": 0.001193664999846078,
"children": {
"RLTrainer._checkpoint": {
"total": 0.2091343179999967,
"count": 1,
"self": 0.2091343179999967
}
}
}
}
}
}
}