Valencio's picture
First Push
28c74b0 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8962612748146057,
"min": 0.8713086843490601,
"max": 2.836738348007202,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8518.0673828125,
"min": 8518.0673828125,
"max": 28957.42578125,
"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": 12.801126480102539,
"min": 0.290190190076828,
"max": 12.82616901397705,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2496.2197265625,
"min": 56.296897888183594,
"max": 2616.53857421875,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06658316069304276,
"min": 0.06342197155211972,
"max": 0.07523977272962928,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.26633264277217106,
"min": 0.2536878862084789,
"max": 0.37039418358472176,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21825000073979883,
"min": 0.11034464259978895,
"max": 0.2956393060146594,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8730000029591953,
"min": 0.4413785703991558,
"max": 1.4045732015488193,
"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": 25.045454545454547,
"min": 3.1136363636363638,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1102.0,
"min": 137.0,
"max": 1396.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.045454545454547,
"min": 3.1136363636363638,
"max": 25.381818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1102.0,
"min": 137.0,
"max": 1396.0,
"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": "1765145782",
"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": "2.8.0+cu128",
"numpy_version": "1.23.5",
"end_time_seconds": "1765146238"
},
"total": 455.952887218,
"count": 1,
"self": 0.4327826379999351,
"children": {
"run_training.setup": {
"total": 0.029302170000050864,
"count": 1,
"self": 0.029302170000050864
},
"TrainerController.start_learning": {
"total": 455.49080241,
"count": 1,
"self": 0.349669913003936,
"children": {
"TrainerController._reset_env": {
"total": 2.9664259390000325,
"count": 1,
"self": 2.9664259390000325
},
"TrainerController.advance": {
"total": 452.07371720099616,
"count": 18192,
"self": 0.3814944459969638,
"children": {
"env_step": {
"total": 329.9574486469885,
"count": 18192,
"self": 258.1545333709797,
"children": {
"SubprocessEnvManager._take_step": {
"total": 71.58862456600934,
"count": 18192,
"self": 1.2708221940125668,
"children": {
"TorchPolicy.evaluate": {
"total": 70.31780237199678,
"count": 18192,
"self": 70.31780237199678
}
}
},
"workers": {
"total": 0.21429070999943178,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.73905945501235,
"count": 18192,
"is_parallel": true,
"self": 226.3689523310178,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.004944313999999395,
"count": 1,
"is_parallel": true,
"self": 0.003519943000128478,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014243709998709164,
"count": 10,
"is_parallel": true,
"self": 0.0014243709998709164
}
}
},
"UnityEnvironment.step": {
"total": 0.08808149900005446,
"count": 1,
"is_parallel": true,
"self": 0.0006420700000262514,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0005841229999532516,
"count": 1,
"is_parallel": true,
"self": 0.0005841229999532516
},
"communicator.exchange": {
"total": 0.08131556000000728,
"count": 1,
"is_parallel": true,
"self": 0.08131556000000728
},
"steps_from_proto": {
"total": 0.00553974600006768,
"count": 1,
"is_parallel": true,
"self": 0.00036992200023178157,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.005169823999835899,
"count": 10,
"is_parallel": true,
"self": 0.005169823999835899
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 227.37010712399456,
"count": 18191,
"is_parallel": true,
"self": 10.810098576010773,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.750997670001539,
"count": 18191,
"is_parallel": true,
"self": 5.750997670001539
},
"communicator.exchange": {
"total": 171.96452195399343,
"count": 18191,
"is_parallel": true,
"self": 171.96452195399343
},
"steps_from_proto": {
"total": 38.84448892398882,
"count": 18191,
"is_parallel": true,
"self": 6.987591431047008,
"children": {
"_process_rank_one_or_two_observation": {
"total": 31.856897492941812,
"count": 181910,
"is_parallel": true,
"self": 31.856897492941812
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 121.7347741080107,
"count": 18192,
"self": 0.42431905200476194,
"children": {
"process_trajectory": {
"total": 27.101086195005905,
"count": 18192,
"self": 26.59476964300586,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5063165520000439,
"count": 4,
"self": 0.5063165520000439
}
}
},
"_update_policy": {
"total": 94.20936886100003,
"count": 90,
"self": 38.831035416000304,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.378333444999726,
"count": 4587,
"self": 55.378333444999726
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.1439999525464373e-06,
"count": 1,
"self": 1.1439999525464373e-06
},
"TrainerController._save_models": {
"total": 0.10098821299993688,
"count": 1,
"self": 0.0008371489998353354,
"children": {
"RLTrainer._checkpoint": {
"total": 0.10015106400010154,
"count": 1,
"self": 0.10015106400010154
}
}
}
}
}
}
}