amblecoder's picture
First Push
192797a verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9148258566856384,
"min": 0.9053372740745544,
"max": 2.8572182655334473,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8694.5048828125,
"min": 8694.5048828125,
"max": 29166.484375,
"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": 12.117987632751465,
"min": 0.4991791844367981,
"max": 12.117987632751465,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2363.007568359375,
"min": 96.84075927734375,
"max": 2466.0029296875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07195598241021656,
"min": 0.06060342136961659,
"max": 0.07647628036747668,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2878239296408662,
"min": 0.24241368547846637,
"max": 0.3627634711407225,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.1817778737521639,
"min": 0.12053456012040888,
"max": 0.29430807770467265,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7271114950086556,
"min": 0.4821382404816355,
"max": 1.4715403885233633,
"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": 23.727272727272727,
"min": 3.75,
"max": 23.763636363636362,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1044.0,
"min": 165.0,
"max": 1307.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 23.727272727272727,
"min": 3.75,
"max": 23.763636363636362,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1044.0,
"min": 165.0,
"max": 1307.0,
"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": "1747017549",
"python_version": "3.10.12 (main, Jul 5 2023, 18:54:27) [GCC 11.2.0]",
"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": "1.2.0.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": "1747017992"
},
"total": 442.66169434899984,
"count": 1,
"self": 0.7110418389997903,
"children": {
"run_training.setup": {
"total": 0.021856995000007373,
"count": 1,
"self": 0.021856995000007373
},
"TrainerController.start_learning": {
"total": 441.92879551500005,
"count": 1,
"self": 0.376216179983885,
"children": {
"TrainerController._reset_env": {
"total": 3.4785135240001637,
"count": 1,
"self": 3.4785135240001637
},
"TrainerController.advance": {
"total": 437.9465910580159,
"count": 18192,
"self": 0.3800215860364915,
"children": {
"env_step": {
"total": 313.10954655099863,
"count": 18192,
"self": 239.61239611400197,
"children": {
"SubprocessEnvManager._take_step": {
"total": 73.28700892099278,
"count": 18192,
"self": 1.2849774649976098,
"children": {
"TorchPolicy.evaluate": {
"total": 72.00203145599517,
"count": 18192,
"self": 72.00203145599517
}
}
},
"workers": {
"total": 0.21014151600388686,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 440.45200213998396,
"count": 18192,
"is_parallel": true,
"self": 230.3989531649877,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005503779000036957,
"count": 1,
"is_parallel": true,
"self": 0.003446774999929403,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002057004000107554,
"count": 10,
"is_parallel": true,
"self": 0.002057004000107554
}
}
},
"UnityEnvironment.step": {
"total": 0.04034192499989331,
"count": 1,
"is_parallel": true,
"self": 0.0006397189999916009,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004256649999661022,
"count": 1,
"is_parallel": true,
"self": 0.0004256649999661022
},
"communicator.exchange": {
"total": 0.0374951339999825,
"count": 1,
"is_parallel": true,
"self": 0.0374951339999825
},
"steps_from_proto": {
"total": 0.0017814069999531057,
"count": 1,
"is_parallel": true,
"self": 0.0003786499999023363,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014027570000507694,
"count": 10,
"is_parallel": true,
"self": 0.0014027570000507694
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 210.05304897499627,
"count": 18191,
"is_parallel": true,
"self": 9.889538388011488,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.576686486974722,
"count": 18191,
"is_parallel": true,
"self": 5.576686486974722
},
"communicator.exchange": {
"total": 161.70001189199184,
"count": 18191,
"is_parallel": true,
"self": 161.70001189199184
},
"steps_from_proto": {
"total": 32.88681220801823,
"count": 18191,
"is_parallel": true,
"self": 5.961305116029052,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.925507091989175,
"count": 181910,
"is_parallel": true,
"self": 26.925507091989175
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 124.45702292098076,
"count": 18192,
"self": 0.4436514229983004,
"children": {
"process_trajectory": {
"total": 28.47313066298284,
"count": 18192,
"self": 27.981702935982867,
"children": {
"RLTrainer._checkpoint": {
"total": 0.49142772699997295,
"count": 4,
"self": 0.49142772699997295
}
}
},
"_update_policy": {
"total": 95.54024083499962,
"count": 90,
"self": 39.17970401199932,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.3605368230003,
"count": 4587,
"self": 56.3605368230003
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.193000116472831e-06,
"count": 1,
"self": 1.193000116472831e-06
},
"TrainerController._save_models": {
"total": 0.12747355999999854,
"count": 1,
"self": 0.0011184200000116107,
"children": {
"RLTrainer._checkpoint": {
"total": 0.12635513999998693,
"count": 1,
"self": 0.12635513999998693
}
}
}
}
}
}
}