andge's picture
First push
4537489
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.986693799495697,
"min": 0.9864693880081177,
"max": 2.8708274364471436,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9420.9521484375,
"min": 9420.9521484375,
"max": 29400.142578125,
"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": 11.92142391204834,
"min": 0.34224995970726013,
"max": 11.92142391204834,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2324.677734375,
"min": 66.39649200439453,
"max": 2416.216796875,
"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": 0.0688434930889611,
"min": 0.06189062447012082,
"max": 0.07511734046160665,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2753739723558444,
"min": 0.2475624978804833,
"max": 0.3755867023080332,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.19870182652683818,
"min": 0.11253961448457238,
"max": 0.26965630105605315,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7948073061073527,
"min": 0.4501584579382895,
"max": 1.3106744087794249,
"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": 23.818181818181817,
"min": 3.340909090909091,
"max": 23.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1048.0,
"min": 147.0,
"max": 1290.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.818181818181817,
"min": 3.340909090909091,
"max": 23.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1048.0,
"min": 147.0,
"max": 1290.0,
"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": "1676277144",
"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": "1.21.6",
"end_time_seconds": "1676277585"
},
"total": 440.8209951650001,
"count": 1,
"self": 0.41355626600034157,
"children": {
"run_training.setup": {
"total": 0.10923031499987701,
"count": 1,
"self": 0.10923031499987701
},
"TrainerController.start_learning": {
"total": 440.2982085839999,
"count": 1,
"self": 0.498962511051559,
"children": {
"TrainerController._reset_env": {
"total": 9.55287369000007,
"count": 1,
"self": 9.55287369000007
},
"TrainerController.advance": {
"total": 430.11728310894796,
"count": 18201,
"self": 0.24681290493572305,
"children": {
"env_step": {
"total": 429.87047020401224,
"count": 18201,
"self": 295.5203636340211,
"children": {
"SubprocessEnvManager._take_step": {
"total": 134.09698407300493,
"count": 18201,
"self": 1.35788150801136,
"children": {
"TorchPolicy.evaluate": {
"total": 132.73910256499357,
"count": 18201,
"self": 29.445346480005355,
"children": {
"TorchPolicy.sample_actions": {
"total": 103.29375608498822,
"count": 18201,
"self": 103.29375608498822
}
}
}
}
},
"workers": {
"total": 0.2531224969861796,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 438.82583063999164,
"count": 18201,
"is_parallel": true,
"self": 211.19186352001134,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005352278999907867,
"count": 1,
"is_parallel": true,
"self": 0.0032928529999480816,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0020594259999597853,
"count": 10,
"is_parallel": true,
"self": 0.0020594259999597853
}
}
},
"UnityEnvironment.step": {
"total": 0.05011252999975113,
"count": 1,
"is_parallel": true,
"self": 0.00057374699963475,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00036864100002276246,
"count": 1,
"is_parallel": true,
"self": 0.00036864100002276246
},
"communicator.exchange": {
"total": 0.0474022800003695,
"count": 1,
"is_parallel": true,
"self": 0.0474022800003695
},
"steps_from_proto": {
"total": 0.0017678619997241185,
"count": 1,
"is_parallel": true,
"self": 0.00042025999891848187,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013476020008056366,
"count": 10,
"is_parallel": true,
"self": 0.0013476020008056366
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.6339671199803,
"count": 18200,
"is_parallel": true,
"self": 9.107134753019182,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 4.970621559986739,
"count": 18200,
"is_parallel": true,
"self": 4.970621559986739
},
"communicator.exchange": {
"total": 181.2703266009903,
"count": 18200,
"is_parallel": true,
"self": 181.2703266009903
},
"steps_from_proto": {
"total": 32.285884205984075,
"count": 18200,
"is_parallel": true,
"self": 6.482690813822501,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.803193392161575,
"count": 182000,
"is_parallel": true,
"self": 25.803193392161575
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012575500022649067,
"count": 1,
"self": 0.00012575500022649067,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 427.05305912577387,
"count": 383266,
"is_parallel": true,
"self": 9.029878464017202,
"children": {
"process_trajectory": {
"total": 246.69530845875488,
"count": 383266,
"is_parallel": true,
"self": 245.22228506675447,
"children": {
"RLTrainer._checkpoint": {
"total": 1.4730233920004139,
"count": 4,
"is_parallel": true,
"self": 1.4730233920004139
}
}
},
"_update_policy": {
"total": 171.3278722030018,
"count": 90,
"is_parallel": true,
"self": 59.3239211230125,
"children": {
"TorchPPOOptimizer.update": {
"total": 112.00395107998929,
"count": 4587,
"is_parallel": true,
"self": 112.00395107998929
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.12896351900008085,
"count": 1,
"self": 0.00087881900026332,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12808469999981753,
"count": 1,
"self": 0.12808469999981753
}
}
}
}
}
}
}