ying01's picture
First Push
a9f1445 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.7599307894706726,
"min": 0.7599307894706726,
"max": 2.8550302982330322,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 7222.38232421875,
"min": 7222.38232421875,
"max": 29144.1484375,
"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": 12.784159660339355,
"min": 0.43743467330932617,
"max": 12.784159660339355,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2492.9111328125,
"min": 84.8623275756836,
"max": 2598.67919921875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06409671441453575,
"min": 0.060979588599901255,
"max": 0.07429221014642867,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.256386857658143,
"min": 0.24391835439960502,
"max": 0.36195651676940077,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21284752675131255,
"min": 0.13611026021524097,
"max": 0.3050449409905602,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8513901070052502,
"min": 0.5444410408609639,
"max": 1.525224704952801,
"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.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.Environment.CumulativeReward.mean": {
"value": 25.431818181818183,
"min": 3.409090909090909,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1119.0,
"min": 150.0,
"max": 1394.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.431818181818183,
"min": 3.409090909090909,
"max": 25.431818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1119.0,
"min": 150.0,
"max": 1394.0,
"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": "1747393909",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.2.0.dev0",
"mlagents_envs_version": "1.2.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.7.0+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1747394345"
},
"total": 435.9678424509998,
"count": 1,
"self": 0.8446306219998405,
"children": {
"run_training.setup": {
"total": 0.02389508999976897,
"count": 1,
"self": 0.02389508999976897
},
"TrainerController.start_learning": {
"total": 435.0993167390002,
"count": 1,
"self": 0.3818448950255515,
"children": {
"TrainerController._reset_env": {
"total": 3.7343423040001653,
"count": 1,
"self": 3.7343423040001653
},
"TrainerController.advance": {
"total": 430.85352099697457,
"count": 18192,
"self": 0.41033295197530606,
"children": {
"env_step": {
"total": 304.851659533007,
"count": 18192,
"self": 233.24388448803893,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.38663950297632,
"count": 18192,
"self": 1.2857990059892472,
"children": {
"TorchPolicy.evaluate": {
"total": 70.10084049698708,
"count": 18192,
"self": 70.10084049698708
}
}
},
"workers": {
"total": 0.22113554199177088,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 433.5223951499688,
"count": 18192,
"is_parallel": true,
"self": 228.77607352694622,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.00673443400000906,
"count": 1,
"is_parallel": true,
"self": 0.005313196999850334,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001421237000158726,
"count": 10,
"is_parallel": true,
"self": 0.001421237000158726
}
}
},
"UnityEnvironment.step": {
"total": 0.06330518999993728,
"count": 1,
"is_parallel": true,
"self": 0.0005932969997957116,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0003839430000880384,
"count": 1,
"is_parallel": true,
"self": 0.0003839430000880384
},
"communicator.exchange": {
"total": 0.060366429000168864,
"count": 1,
"is_parallel": true,
"self": 0.060366429000168864
},
"steps_from_proto": {
"total": 0.0019615209998846694,
"count": 1,
"is_parallel": true,
"self": 0.000383614999918791,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015779059999658784,
"count": 10,
"is_parallel": true,
"self": 0.0015779059999658784
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 204.7463216230226,
"count": 18191,
"is_parallel": true,
"self": 9.850100185979045,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.404866477028008,
"count": 18191,
"is_parallel": true,
"self": 5.404866477028008
},
"communicator.exchange": {
"total": 158.0101028740246,
"count": 18191,
"is_parallel": true,
"self": 158.0101028740246
},
"steps_from_proto": {
"total": 31.481252085990945,
"count": 18191,
"is_parallel": true,
"self": 5.654672018034034,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.82658006795691,
"count": 181910,
"is_parallel": true,
"self": 25.82658006795691
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 125.59152851199224,
"count": 18192,
"self": 0.4734691810235745,
"children": {
"process_trajectory": {
"total": 27.887933979966874,
"count": 18192,
"self": 27.38040426996713,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5075297099997442,
"count": 4,
"self": 0.5075297099997442
}
}
},
"_update_policy": {
"total": 97.23012535100179,
"count": 90,
"self": 40.250509623992,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.97961572700979,
"count": 4587,
"self": 56.97961572700979
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.3109997780702543e-06,
"count": 1,
"self": 1.3109997780702543e-06
},
"TrainerController._save_models": {
"total": 0.1296072320001258,
"count": 1,
"self": 0.0011302520001663652,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12847697999995944,
"count": 1,
"self": 0.12847697999995944
}
}
}
}
}
}
}