alvarobb's picture
Basic snowball with standard params
cfa1ddc
raw
history blame contribute delete
No virus
18.5 kB
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.1056851148605347,
"min": 1.1056851148605347,
"max": 2.850186586380005,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 10569.244140625,
"min": 10569.244140625,
"max": 29251.46484375,
"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": 12.456445693969727,
"min": 0.3481903076171875,
"max": 12.456445693969727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2429.0068359375,
"min": 67.54891967773438,
"max": 2497.77001953125,
"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": 0.0691104212745296,
"min": 0.06281771210073131,
"max": 0.07240367722360865,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2764416850981184,
"min": 0.25127084840292524,
"max": 0.35988411664684283,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18468303204167125,
"min": 0.11375185094235063,
"max": 0.274674652429188,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.738732128166685,
"min": 0.4550074037694025,
"max": 1.37337326214594,
"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": 25.09090909090909,
"min": 3.2045454545454546,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1104.0,
"min": 141.0,
"max": 1323.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.09090909090909,
"min": 3.2045454545454546,
"max": 25.09090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1104.0,
"min": 141.0,
"max": 1323.0,
"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": "1681660093",
"python_version": "3.9.16 (main, Dec 7 2022, 01:11:51) \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": "0.31.0.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": "1681660601"
},
"total": 508.00376889799986,
"count": 1,
"self": 0.4362607419998312,
"children": {
"run_training.setup": {
"total": 0.11800310000000991,
"count": 1,
"self": 0.11800310000000991
},
"TrainerController.start_learning": {
"total": 507.449505056,
"count": 1,
"self": 0.6547875689992679,
"children": {
"TrainerController._reset_env": {
"total": 4.181046296999966,
"count": 1,
"self": 4.181046296999966
},
"TrainerController.advance": {
"total": 502.4800226330008,
"count": 18202,
"self": 0.33959283000103824,
"children": {
"env_step": {
"total": 502.14042980299973,
"count": 18202,
"self": 368.2521668739829,
"children": {
"SubprocessEnvManager._take_step": {
"total": 133.51145132701913,
"count": 18202,
"self": 1.8545468850198858,
"children": {
"TorchPolicy.evaluate": {
"total": 131.65690444199925,
"count": 18202,
"self": 131.65690444199925
}
}
},
"workers": {
"total": 0.3768116019977015,
"count": 18202,
"self": 0.0,
"children": {
"worker_root": {
"total": 505.7170270650073,
"count": 18202,
"is_parallel": true,
"self": 228.99988575298096,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005680577000021003,
"count": 1,
"is_parallel": true,
"self": 0.003820578000045316,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018599989999756872,
"count": 10,
"is_parallel": true,
"self": 0.0018599989999756872
}
}
},
"UnityEnvironment.step": {
"total": 0.06450240699996357,
"count": 1,
"is_parallel": true,
"self": 0.0006564650000200345,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00041836900004454947,
"count": 1,
"is_parallel": true,
"self": 0.00041836900004454947
},
"communicator.exchange": {
"total": 0.060278934999928424,
"count": 1,
"is_parallel": true,
"self": 0.060278934999928424
},
"steps_from_proto": {
"total": 0.0031486379999705605,
"count": 1,
"is_parallel": true,
"self": 0.00040923999983988324,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027393980001306772,
"count": 10,
"is_parallel": true,
"self": 0.0027393980001306772
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 276.71714131202634,
"count": 18201,
"is_parallel": true,
"self": 10.980476504044418,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.853643969990003,
"count": 18201,
"is_parallel": true,
"self": 5.853643969990003
},
"communicator.exchange": {
"total": 224.39834279699846,
"count": 18201,
"is_parallel": true,
"self": 224.39834279699846
},
"steps_from_proto": {
"total": 35.48467804099346,
"count": 18201,
"is_parallel": true,
"self": 7.259940466963712,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.224737574029746,
"count": 182010,
"is_parallel": true,
"self": 28.224737574029746
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001708899999357527,
"count": 1,
"self": 0.0001708899999357527,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 498.4752673780249,
"count": 461468,
"is_parallel": true,
"self": 11.887625534151084,
"children": {
"process_trajectory": {
"total": 273.91806913787434,
"count": 461468,
"is_parallel": true,
"self": 273.12640658787416,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7916625500001828,
"count": 4,
"is_parallel": true,
"self": 0.7916625500001828
}
}
},
"_update_policy": {
"total": 212.66957270599949,
"count": 90,
"is_parallel": true,
"self": 78.35518517100718,
"children": {
"TorchPPOOptimizer.update": {
"total": 134.3143875349923,
"count": 4587,
"is_parallel": true,
"self": 134.3143875349923
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13347766700007924,
"count": 1,
"self": 0.0009793219999210123,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13249834500015822,
"count": 1,
"self": 0.13249834500015822
}
}
}
}
}
}
}