ThatOneSkyler's picture
First Push
b78a1c4 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8786922693252563,
"min": 0.8786922693252563,
"max": 2.8745572566986084,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8380.087890625,
"min": 8380.087890625,
"max": 29438.33984375,
"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": 12.955521583557129,
"min": 0.2567858099937439,
"max": 12.955521583557129,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2526.32666015625,
"min": 49.816444396972656,
"max": 2629.7099609375,
"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": 0.07415114224668108,
"min": 0.061770306495143854,
"max": 0.07605011759241118,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2966045689867243,
"min": 0.26340403678706004,
"max": 0.36644136751419865,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20771927057820205,
"min": 0.10136745781089891,
"max": 0.2902146818883279,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8308770823128082,
"min": 0.40546983124359565,
"max": 1.294997054572199,
"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": 25.727272727272727,
"min": 3.090909090909091,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1132.0,
"min": 136.0,
"max": 1386.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.727272727272727,
"min": 3.090909090909091,
"max": 25.727272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1132.0,
"min": 136.0,
"max": 1386.0,
"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": "1715671734",
"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": "1715672178"
},
"total": 444.50213279900004,
"count": 1,
"self": 0.5425148110001032,
"children": {
"run_training.setup": {
"total": 0.056943050999962,
"count": 1,
"self": 0.056943050999962
},
"TrainerController.start_learning": {
"total": 443.902674937,
"count": 1,
"self": 0.5612349970010087,
"children": {
"TrainerController._reset_env": {
"total": 2.855972780000002,
"count": 1,
"self": 2.855972780000002
},
"TrainerController.advance": {
"total": 440.39833880499884,
"count": 18199,
"self": 0.26602032100038286,
"children": {
"env_step": {
"total": 440.13231848399846,
"count": 18199,
"self": 287.7492199040007,
"children": {
"SubprocessEnvManager._take_step": {
"total": 152.1007010269978,
"count": 18199,
"self": 1.4850885999944126,
"children": {
"TorchPolicy.evaluate": {
"total": 150.61561242700338,
"count": 18199,
"self": 150.61561242700338
}
}
},
"workers": {
"total": 0.28239755299995295,
"count": 18199,
"self": 0.0,
"children": {
"worker_root": {
"total": 442.76287080799955,
"count": 18199,
"is_parallel": true,
"self": 222.5010299799905,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005564084000013736,
"count": 1,
"is_parallel": true,
"self": 0.003989816000000701,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001574268000013035,
"count": 10,
"is_parallel": true,
"self": 0.001574268000013035
}
}
},
"UnityEnvironment.step": {
"total": 0.06114595700000791,
"count": 1,
"is_parallel": true,
"self": 0.0007769579999603593,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.000425462000009702,
"count": 1,
"is_parallel": true,
"self": 0.000425462000009702
},
"communicator.exchange": {
"total": 0.05765727000004972,
"count": 1,
"is_parallel": true,
"self": 0.05765727000004972
},
"steps_from_proto": {
"total": 0.002286266999988129,
"count": 1,
"is_parallel": true,
"self": 0.0005884500001229753,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016978169998651538,
"count": 10,
"is_parallel": true,
"self": 0.0016978169998651538
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 220.26184082800904,
"count": 18198,
"is_parallel": true,
"self": 10.07232816001158,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.208162684999934,
"count": 18198,
"is_parallel": true,
"self": 5.208162684999934
},
"communicator.exchange": {
"total": 172.81744457999736,
"count": 18198,
"is_parallel": true,
"self": 172.81744457999736
},
"steps_from_proto": {
"total": 32.16390540300017,
"count": 18198,
"is_parallel": true,
"self": 6.03502700000962,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.12887840299055,
"count": 181980,
"is_parallel": true,
"self": 26.12887840299055
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00012566300006255915,
"count": 1,
"self": 0.00012566300006255915,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 435.1614111120122,
"count": 651528,
"is_parallel": true,
"self": 13.372022104992709,
"children": {
"process_trajectory": {
"total": 240.9395658390194,
"count": 651528,
"is_parallel": true,
"self": 240.11551196601937,
"children": {
"RLTrainer._checkpoint": {
"total": 0.8240538730000253,
"count": 4,
"is_parallel": true,
"self": 0.8240538730000253
}
}
},
"_update_policy": {
"total": 180.8498231680001,
"count": 90,
"is_parallel": true,
"self": 57.10771812299987,
"children": {
"TorchPPOOptimizer.update": {
"total": 123.74210504500024,
"count": 4587,
"is_parallel": true,
"self": 123.74210504500024
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.0870026920000555,
"count": 1,
"self": 0.0009895100000676393,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08601318199998786,
"count": 1,
"self": 0.08601318199998786
}
}
}
}
}
}
}