blakepritchard's picture
First Push
0acc927 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.9453418850898743,
"min": 0.9403722286224365,
"max": 2.8259544372558594,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8984.529296875,
"min": 8984.529296875,
"max": 28847.341796875,
"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": 13.000679969787598,
"min": 0.41044360399246216,
"max": 13.000679969787598,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2535.132568359375,
"min": 79.62606048583984,
"max": 2638.04345703125,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07187305659599409,
"min": 0.06344035838196492,
"max": 0.08068806719672342,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28749222638397637,
"min": 0.2635438276555243,
"max": 0.36902419340285453,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2116689634527646,
"min": 0.13462733861182213,
"max": 0.29079839867704055,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8466758538110584,
"min": 0.5385093544472885,
"max": 1.4539919933852028,
"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": 25.704545454545453,
"min": 4.090909090909091,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1131.0,
"min": 180.0,
"max": 1420.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.704545454545453,
"min": 4.090909090909091,
"max": 25.818181818181817,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1131.0,
"min": 180.0,
"max": 1420.0,
"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": "1752460928",
"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": "2.7.1+cu126",
"numpy_version": "1.23.5",
"end_time_seconds": "1752461391"
},
"total": 462.8034920690002,
"count": 1,
"self": 0.4883308880000641,
"children": {
"run_training.setup": {
"total": 0.023017463000087446,
"count": 1,
"self": 0.023017463000087446
},
"TrainerController.start_learning": {
"total": 462.29214371800003,
"count": 1,
"self": 0.43922589400199286,
"children": {
"TrainerController._reset_env": {
"total": 3.062228700000105,
"count": 1,
"self": 3.062228700000105
},
"TrainerController.advance": {
"total": 458.70093527699805,
"count": 18192,
"self": 0.4735051969983033,
"children": {
"env_step": {
"total": 334.80560618101026,
"count": 18192,
"self": 258.3634444470333,
"children": {
"SubprocessEnvManager._take_step": {
"total": 76.17253690098687,
"count": 18192,
"self": 1.4057461679806238,
"children": {
"TorchPolicy.evaluate": {
"total": 74.76679073300625,
"count": 18192,
"self": 74.76679073300625
}
}
},
"workers": {
"total": 0.26962483299007545,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 460.6396333269697,
"count": 18192,
"is_parallel": true,
"self": 234.20879437693247,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.005863219000048048,
"count": 1,
"is_parallel": true,
"self": 0.003548674000057872,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0023145449999901757,
"count": 10,
"is_parallel": true,
"self": 0.0023145449999901757
}
}
},
"UnityEnvironment.step": {
"total": 0.036135871999931624,
"count": 1,
"is_parallel": true,
"self": 0.0005725769999571639,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004310300000724965,
"count": 1,
"is_parallel": true,
"self": 0.0004310300000724965
},
"communicator.exchange": {
"total": 0.03336648499998773,
"count": 1,
"is_parallel": true,
"self": 0.03336648499998773
},
"steps_from_proto": {
"total": 0.0017657799999142298,
"count": 1,
"is_parallel": true,
"self": 0.0003509389996452228,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001414841000269007,
"count": 10,
"is_parallel": true,
"self": 0.001414841000269007
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 226.43083895003724,
"count": 18191,
"is_parallel": true,
"self": 10.211828355999387,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.777144736023274,
"count": 18191,
"is_parallel": true,
"self": 5.777144736023274
},
"communicator.exchange": {
"total": 176.25970298900597,
"count": 18191,
"is_parallel": true,
"self": 176.25970298900597
},
"steps_from_proto": {
"total": 34.18216286900861,
"count": 18191,
"is_parallel": true,
"self": 6.315149049917409,
"children": {
"_process_rank_one_or_two_observation": {
"total": 27.8670138190912,
"count": 181910,
"is_parallel": true,
"self": 27.8670138190912
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 123.42182389898949,
"count": 18192,
"self": 0.5504824409708817,
"children": {
"process_trajectory": {
"total": 27.75426250701821,
"count": 18192,
"self": 27.34620818701842,
"children": {
"RLTrainer._checkpoint": {
"total": 0.4080543199997919,
"count": 4,
"self": 0.4080543199997919
}
}
},
"_update_policy": {
"total": 95.1170789510004,
"count": 90,
"self": 39.207466089004356,
"children": {
"TorchPPOOptimizer.update": {
"total": 55.90961286199604,
"count": 4587,
"self": 55.90961286199604
}
}
}
}
}
}
},
"trainer_threads": {
"total": 9.979999049392063e-07,
"count": 1,
"self": 9.979999049392063e-07
},
"TrainerController._save_models": {
"total": 0.0897528489999786,
"count": 1,
"self": 0.0009180530000776344,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08883479599990096,
"count": 1,
"self": 0.08883479599990096
}
}
}
}
}
}
}