nickmiller795's picture
First Push
7f8708c verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8411333560943604,
"min": 0.8411333560943604,
"max": 2.8673911094665527,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8040.3935546875,
"min": 8040.3935546875,
"max": 29364.953125,
"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": 12.627050399780273,
"min": 0.3279537856578827,
"max": 12.627050399780273,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2462.27490234375,
"min": 63.6230354309082,
"max": 2535.584228515625,
"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": 0.05934086202140344,
"min": 0.05934086202140344,
"max": 0.07348133435438037,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.23736344808561377,
"min": 0.23736344808561377,
"max": 0.35924989932516166,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.21054527835518708,
"min": 0.1113924600775171,
"max": 0.2798975355484907,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8421811134207483,
"min": 0.4455698403100684,
"max": 1.3821865726335376,
"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": 24.818181818181817,
"min": 3.1136363636363638,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1092.0,
"min": 137.0,
"max": 1388.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.818181818181817,
"min": 3.1136363636363638,
"max": 25.236363636363638,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1092.0,
"min": 137.0,
"max": 1388.0,
"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": "1707630725",
"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": "2.2.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1707631182"
},
"total": 456.55438694299994,
"count": 1,
"self": 0.436439590999953,
"children": {
"run_training.setup": {
"total": 0.051150548999999046,
"count": 1,
"self": 0.051150548999999046
},
"TrainerController.start_learning": {
"total": 456.066796803,
"count": 1,
"self": 0.5706294549995619,
"children": {
"TrainerController._reset_env": {
"total": 3.5476521809999895,
"count": 1,
"self": 3.5476521809999895
},
"TrainerController.advance": {
"total": 451.8584520090004,
"count": 18200,
"self": 0.2846297770008732,
"children": {
"env_step": {
"total": 451.57382223199954,
"count": 18200,
"self": 292.9509888830073,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.3343288279906,
"count": 18200,
"self": 1.4868980049842548,
"children": {
"TorchPolicy.evaluate": {
"total": 156.84743082300633,
"count": 18200,
"self": 156.84743082300633
}
}
},
"workers": {
"total": 0.2885045210016415,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 454.8530626340066,
"count": 18200,
"is_parallel": true,
"self": 226.2570815139867,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006859166000026562,
"count": 1,
"is_parallel": true,
"self": 0.004129508000232818,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0027296579997937442,
"count": 10,
"is_parallel": true,
"self": 0.0027296579997937442
}
}
},
"UnityEnvironment.step": {
"total": 0.043422002000056636,
"count": 1,
"is_parallel": true,
"self": 0.0006916819999105428,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004994949999854725,
"count": 1,
"is_parallel": true,
"self": 0.0004994949999854725
},
"communicator.exchange": {
"total": 0.03996106300007796,
"count": 1,
"is_parallel": true,
"self": 0.03996106300007796
},
"steps_from_proto": {
"total": 0.0022697620000826646,
"count": 1,
"is_parallel": true,
"self": 0.0004309729999931733,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0018387890000894913,
"count": 10,
"is_parallel": true,
"self": 0.0018387890000894913
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 228.59598112001993,
"count": 18199,
"is_parallel": true,
"self": 11.019061219016521,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.752297808005892,
"count": 18199,
"is_parallel": true,
"self": 5.752297808005892
},
"communicator.exchange": {
"total": 176.19726496799706,
"count": 18199,
"is_parallel": true,
"self": 176.19726496799706
},
"steps_from_proto": {
"total": 35.62735712500046,
"count": 18199,
"is_parallel": true,
"self": 6.55630659499684,
"children": {
"_process_rank_one_or_two_observation": {
"total": 29.071050530003617,
"count": 181990,
"is_parallel": true,
"self": 29.071050530003617
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 3.553199996986223e-05,
"count": 1,
"self": 3.553199996986223e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.01254312496815,
"count": 674100,
"is_parallel": true,
"self": 15.911575768979787,
"children": {
"process_trajectory": {
"total": 245.5972522809891,
"count": 674100,
"is_parallel": true,
"self": 245.08067218098927,
"children": {
"RLTrainer._checkpoint": {
"total": 0.5165800999998282,
"count": 4,
"is_parallel": true,
"self": 0.5165800999998282
}
}
},
"_update_policy": {
"total": 184.50371507499926,
"count": 90,
"is_parallel": true,
"self": 51.57419399300397,
"children": {
"TorchPPOOptimizer.update": {
"total": 132.9295210819953,
"count": 4587,
"is_parallel": true,
"self": 132.9295210819953
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09002762600005099,
"count": 1,
"self": 0.0009698700000626559,
"children": {
"RLTrainer._checkpoint": {
"total": 0.08905775599998833,
"count": 1,
"self": 0.08905775599998833
}
}
}
}
}
}
}