Abraham007China's picture
First Push
323c9fa verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.026414155960083,
"min": 1.026414155960083,
"max": 2.859302520751953,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9822.783203125,
"min": 9822.783203125,
"max": 29282.1171875,
"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": 12.78466510772705,
"min": 0.5372077226638794,
"max": 12.78466510772705,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2493.009765625,
"min": 104.21829986572266,
"max": 2597.6015625,
"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": 0.06896202051275929,
"min": 0.0639440096211711,
"max": 0.07683229303203168,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27584808205103717,
"min": 0.2557760384846844,
"max": 0.38416146516015837,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20567584541790623,
"min": 0.1485646730631261,
"max": 0.27646732052751616,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8227033816716249,
"min": 0.5942586922525044,
"max": 1.3181946768480188,
"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": 25.181818181818183,
"min": 3.840909090909091,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1108.0,
"min": 169.0,
"max": 1390.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.181818181818183,
"min": 3.840909090909091,
"max": 25.34090909090909,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1108.0,
"min": 169.0,
"max": 1390.0,
"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": "1710368995",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"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": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.2.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1710369448"
},
"total": 453.16962058600006,
"count": 1,
"self": 0.4339934260001428,
"children": {
"run_training.setup": {
"total": 0.052171287999954075,
"count": 1,
"self": 0.052171287999954075
},
"TrainerController.start_learning": {
"total": 452.68345587199997,
"count": 1,
"self": 0.5563102030273512,
"children": {
"TrainerController._reset_env": {
"total": 2.835541854999974,
"count": 1,
"self": 2.835541854999974
},
"TrainerController.advance": {
"total": 449.1930376179728,
"count": 18201,
"self": 0.2698556279519835,
"children": {
"env_step": {
"total": 448.9231819900208,
"count": 18201,
"self": 287.53168126601577,
"children": {
"SubprocessEnvManager._take_step": {
"total": 161.10687349000273,
"count": 18201,
"self": 1.4678430049980307,
"children": {
"TorchPolicy.evaluate": {
"total": 159.6390304850047,
"count": 18201,
"self": 159.6390304850047
}
}
},
"workers": {
"total": 0.2846272340023006,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 451.4648396140092,
"count": 18201,
"is_parallel": true,
"self": 228.3256172010308,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006202885999982755,
"count": 1,
"is_parallel": true,
"self": 0.00451300799954879,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016898780004339642,
"count": 10,
"is_parallel": true,
"self": 0.0016898780004339642
}
}
},
"UnityEnvironment.step": {
"total": 0.07834350200005247,
"count": 1,
"is_parallel": true,
"self": 0.0006714659998579009,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003984350000791892,
"count": 1,
"is_parallel": true,
"self": 0.0003984350000791892
},
"communicator.exchange": {
"total": 0.07508142000006046,
"count": 1,
"is_parallel": true,
"self": 0.07508142000006046
},
"steps_from_proto": {
"total": 0.002192181000054916,
"count": 1,
"is_parallel": true,
"self": 0.0004529299999376235,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0017392510001172923,
"count": 10,
"is_parallel": true,
"self": 0.0017392510001172923
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.13922241297837,
"count": 18200,
"is_parallel": true,
"self": 10.322561513027722,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.398600410980407,
"count": 18200,
"is_parallel": true,
"self": 5.398600410980407
},
"communicator.exchange": {
"total": 172.59394577199123,
"count": 18200,
"is_parallel": true,
"self": 172.59394577199123
},
"steps_from_proto": {
"total": 34.82411471697901,
"count": 18200,
"is_parallel": true,
"self": 6.552469547031251,
"children": {
"_process_rank_one_or_two_observation": {
"total": 28.27164516994776,
"count": 182000,
"is_parallel": true,
"self": 28.27164516994776
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001608439997653477,
"count": 1,
"self": 0.0001608439997653477,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 443.36856295001894,
"count": 690061,
"is_parallel": true,
"self": 15.335688170935782,
"children": {
"process_trajectory": {
"total": 244.7234278520839,
"count": 690061,
"is_parallel": true,
"self": 244.11148712608383,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6119407260000571,
"count": 4,
"is_parallel": true,
"self": 0.6119407260000571
}
}
},
"_update_policy": {
"total": 183.30944692699927,
"count": 90,
"is_parallel": true,
"self": 53.07259549201558,
"children": {
"TorchPPOOptimizer.update": {
"total": 130.2368514349837,
"count": 4587,
"is_parallel": true,
"self": 130.2368514349837
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09840535200009981,
"count": 1,
"self": 0.0010293049999745563,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09737604700012525,
"count": 1,
"self": 0.09737604700012525
}
}
}
}
}
}
}