Slyne's picture
First Push
d8c0da3 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.623161256313324,
"min": 0.5537289381027222,
"max": 2.830124855041504,
"count": 200
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 6416.068359375,
"min": 5398.4521484375,
"max": 28889.9140625,
"count": 200
},
"SnowballTarget.Step.mean": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Step.sum": {
"value": 1999992.0,
"min": 9952.0,
"max": 1999992.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 14.393630981445312,
"min": 0.20410603284835815,
"max": 14.438612937927246,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2950.6943359375,
"min": 39.5965690612793,
"max": 2957.8134765625,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06477168040725576,
"min": 0.058724390476138574,
"max": 0.0783742517883451,
"count": 200
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3238584020362788,
"min": 0.23626466216827635,
"max": 0.384442136733674,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.16838180098463504,
"min": 0.10638201754316505,
"max": 0.28277848491481705,
"count": 200
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8419090049231752,
"min": 0.4255280701726602,
"max": 1.4138924245740851,
"count": 200
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 7.032997656000039e-07,
"min": 7.032997656000039e-07,
"max": 0.00029918820027059994,
"count": 200
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.5164988280000196e-06,
"min": 3.5164988280000196e-06,
"max": 0.0014885160038279998,
"count": 200
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10023440000000002,
"min": 0.10023440000000002,
"max": 0.1997294,
"count": 200
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.5011720000000001,
"min": 0.4029176,
"max": 0.996172,
"count": 200
},
"SnowballTarget.Policy.Beta.mean": {
"value": 2.1696560000000067e-05,
"min": 2.1696560000000067e-05,
"max": 0.004986497059999999,
"count": 200
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.00010848280000000034,
"min": 0.00010848280000000034,
"max": 0.024808982800000004,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 200
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 10945.0,
"min": 8756.0,
"max": 10945.0,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 28.2,
"min": 3.022727272727273,
"max": 28.622222222222224,
"count": 200
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1551.0,
"min": 133.0,
"max": 1556.0,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 28.2,
"min": 3.022727272727273,
"max": 28.622222222222224,
"count": 200
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1551.0,
"min": 133.0,
"max": 1556.0,
"count": 200
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 200
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1740552729",
"python_version": "3.10.9 (main, Mar 1 2023, 18:23:06) [GCC 11.2.0]",
"command_line_arguments": "/home/slyne/anaconda3/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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1740556945"
},
"total": 4216.273593415972,
"count": 1,
"self": 0.32094766898080707,
"children": {
"run_training.setup": {
"total": 0.0402634899946861,
"count": 1,
"self": 0.0402634899946861
},
"TrainerController.start_learning": {
"total": 4215.912382256996,
"count": 1,
"self": 3.6504247981356457,
"children": {
"TrainerController._reset_env": {
"total": 1.8789696369785815,
"count": 1,
"self": 1.8789696369785815
},
"TrainerController.advance": {
"total": 4210.307371405885,
"count": 181864,
"self": 3.202507437847089,
"children": {
"env_step": {
"total": 3033.5589358300203,
"count": 181864,
"self": 2166.419866954908,
"children": {
"SubprocessEnvManager._take_step": {
"total": 864.714996343595,
"count": 181864,
"self": 10.501225749088917,
"children": {
"TorchPolicy.evaluate": {
"total": 854.2137705945061,
"count": 181864,
"self": 854.2137705945061
}
}
},
"workers": {
"total": 2.424072531517595,
"count": 181864,
"self": 0.0,
"children": {
"worker_root": {
"total": 4208.722589894605,
"count": 181864,
"is_parallel": true,
"self": 2257.077544472413,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.0016122939996421337,
"count": 1,
"is_parallel": true,
"self": 0.0005764400702901185,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0010358539293520153,
"count": 10,
"is_parallel": true,
"self": 0.0010358539293520153
}
}
},
"UnityEnvironment.step": {
"total": 0.022166911978274584,
"count": 1,
"is_parallel": true,
"self": 0.00024961994495242834,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00020827300613746047,
"count": 1,
"is_parallel": true,
"self": 0.00020827300613746047
},
"communicator.exchange": {
"total": 0.020774036005605012,
"count": 1,
"is_parallel": true,
"self": 0.020774036005605012
},
"steps_from_proto": {
"total": 0.0009349830215796828,
"count": 1,
"is_parallel": true,
"self": 0.00022955209715291858,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0007054309244267642,
"count": 10,
"is_parallel": true,
"self": 0.0007054309244267642
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 1951.6450454221922,
"count": 181863,
"is_parallel": true,
"self": 43.055626050103456,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 24.53296014521038,
"count": 181863,
"is_parallel": true,
"self": 24.53296014521038
},
"communicator.exchange": {
"total": 1755.9743801663863,
"count": 181863,
"is_parallel": true,
"self": 1755.9743801663863
},
"steps_from_proto": {
"total": 128.0820790604921,
"count": 181863,
"is_parallel": true,
"self": 30.45890517148655,
"children": {
"_process_rank_one_or_two_observation": {
"total": 97.62317388900556,
"count": 1818630,
"is_parallel": true,
"self": 97.62317388900556
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 1173.5459281380172,
"count": 181864,
"self": 4.707836191402748,
"children": {
"process_trajectory": {
"total": 243.80382627662038,
"count": 181864,
"self": 240.3096133437357,
"children": {
"RLTrainer._checkpoint": {
"total": 3.494212932884693,
"count": 40,
"self": 3.494212932884693
}
}
},
"_update_policy": {
"total": 925.034265669994,
"count": 909,
"self": 252.13781444035703,
"children": {
"TorchPPOOptimizer.update": {
"total": 672.896451229637,
"count": 46356,
"self": 672.896451229637
}
}
}
}
}
}
},
"trainer_threads": {
"total": 5.839974619448185e-07,
"count": 1,
"self": 5.839974619448185e-07
},
"TrainerController._save_models": {
"total": 0.07561583200003952,
"count": 1,
"self": 0.0005722700152546167,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0750435619847849,
"count": 1,
"self": 0.0750435619847849
}
}
}
}
}
}
}