Qilex's picture
first try
844ecce
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0278573036193848,
"min": 1.0278573036193848,
"max": 2.8536715507507324,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9813.9814453125,
"min": 9813.9814453125,
"max": 29224.451171875,
"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": 12.363714218139648,
"min": 0.23745664954185486,
"max": 12.363714218139648,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2410.92431640625,
"min": 46.06658935546875,
"max": 2490.952880859375,
"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": 0.07004644742090593,
"min": 0.06336003182428505,
"max": 0.07730729138183604,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.28018578968362373,
"min": 0.2534401272971402,
"max": 0.35984276592395925,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.2303565786603619,
"min": 0.13052906781804802,
"max": 0.26528039463594844,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.9214263146414476,
"min": 0.5221162712721921,
"max": 1.3264019731797423,
"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": 24.181818181818183,
"min": 3.6818181818181817,
"max": 24.527272727272727,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1064.0,
"min": 162.0,
"max": 1349.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 24.181818181818183,
"min": 3.6818181818181817,
"max": 24.527272727272727,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1064.0,
"min": 162.0,
"max": 1349.0,
"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": "1674131642",
"python_version": "3.8.10 (default, Nov 14 2022, 12:59:47) \n[GCC 9.4.0]",
"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": "0.29.0.dev0",
"mlagents_envs_version": "0.29.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.8.1+cu102",
"numpy_version": "1.21.6",
"end_time_seconds": "1674132102"
},
"total": 460.73086792600003,
"count": 1,
"self": 0.43488027800009377,
"children": {
"run_training.setup": {
"total": 0.13634017299995094,
"count": 1,
"self": 0.13634017299995094
},
"TrainerController.start_learning": {
"total": 460.159647475,
"count": 1,
"self": 0.5456710330022361,
"children": {
"TrainerController._reset_env": {
"total": 9.786431633999996,
"count": 1,
"self": 9.786431633999996
},
"TrainerController.advance": {
"total": 449.6867196469978,
"count": 18201,
"self": 0.2866800270003296,
"children": {
"env_step": {
"total": 449.4000396199975,
"count": 18201,
"self": 295.44152191799856,
"children": {
"SubprocessEnvManager._take_step": {
"total": 153.66630063100195,
"count": 18201,
"self": 1.497019363002039,
"children": {
"TorchPolicy.evaluate": {
"total": 152.1692812679999,
"count": 18201,
"self": 34.09769289100399,
"children": {
"TorchPolicy.sample_actions": {
"total": 118.07158837699592,
"count": 18201,
"self": 118.07158837699592
}
}
}
}
},
"workers": {
"total": 0.29221707099696914,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 458.825172049004,
"count": 18201,
"is_parallel": true,
"self": 220.05159480299847,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006824236999989353,
"count": 1,
"is_parallel": true,
"self": 0.00419087400001672,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0026333629999726327,
"count": 10,
"is_parallel": true,
"self": 0.0026333629999726327
}
}
},
"UnityEnvironment.step": {
"total": 0.036205663999965054,
"count": 1,
"is_parallel": true,
"self": 0.0006493839999848205,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00029513800001268464,
"count": 1,
"is_parallel": true,
"self": 0.00029513800001268464
},
"communicator.exchange": {
"total": 0.033179190999987895,
"count": 1,
"is_parallel": true,
"self": 0.033179190999987895
},
"steps_from_proto": {
"total": 0.0020819509999796537,
"count": 1,
"is_parallel": true,
"self": 0.0004733040000814981,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016086469998981556,
"count": 10,
"is_parallel": true,
"self": 0.0016086469998981556
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 238.77357724600552,
"count": 18200,
"is_parallel": true,
"self": 8.892878013011853,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.461618297998257,
"count": 18200,
"is_parallel": true,
"self": 5.461618297998257
},
"communicator.exchange": {
"total": 191.37251336499315,
"count": 18200,
"is_parallel": true,
"self": 191.37251336499315
},
"steps_from_proto": {
"total": 33.04656757000225,
"count": 18200,
"is_parallel": true,
"self": 7.146352875965192,
"children": {
"_process_rank_one_or_two_observation": {
"total": 25.90021469403706,
"count": 182000,
"is_parallel": true,
"self": 25.90021469403706
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 4.581099994993565e-05,
"count": 1,
"self": 4.581099994993565e-05,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 446.3329326930073,
"count": 367529,
"is_parallel": true,
"self": 10.089342543001749,
"children": {
"process_trajectory": {
"total": 256.360675882006,
"count": 367529,
"is_parallel": true,
"self": 255.5746848070059,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7859910750000836,
"count": 4,
"is_parallel": true,
"self": 0.7859910750000836
}
}
},
"_update_policy": {
"total": 179.88291426799958,
"count": 90,
"is_parallel": true,
"self": 44.20129647599856,
"children": {
"TorchPPOOptimizer.update": {
"total": 135.68161779200102,
"count": 4587,
"is_parallel": true,
"self": 135.68161779200102
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.14077935000000252,
"count": 1,
"self": 0.0009221130000014455,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13985723700000108,
"count": 1,
"self": 0.13985723700000108
}
}
}
}
}
}
}