Akihi91's picture
First Push
b6ef031 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8924339413642883,
"min": 0.8924339413642883,
"max": 2.8534202575683594,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8481.6923828125,
"min": 8481.6923828125,
"max": 29127.71484375,
"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": 13.040094375610352,
"min": 0.36507272720336914,
"max": 13.040094375610352,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2542.818359375,
"min": 70.82411193847656,
"max": 2642.0947265625,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07280696296234679,
"min": 0.05945080407186384,
"max": 0.07644996772047735,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.29122785184938715,
"min": 0.23780321628745535,
"max": 0.3783183939419412,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18741600511266904,
"min": 0.1282786091803299,
"max": 0.30293124458369086,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7496640204506761,
"min": 0.5131144367213196,
"max": 1.5146562229184544,
"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": 25.931818181818183,
"min": 3.5681818181818183,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1141.0,
"min": 157.0,
"max": 1418.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.931818181818183,
"min": 3.5681818181818183,
"max": 25.931818181818183,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1141.0,
"min": 157.0,
"max": 1418.0,
"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": "1743592345",
"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": "2.6.0+cu124",
"numpy_version": "1.23.5",
"end_time_seconds": "1743592757"
},
"total": 412.051356167,
"count": 1,
"self": 0.4382693359999621,
"children": {
"run_training.setup": {
"total": 0.03155502599997817,
"count": 1,
"self": 0.03155502599997817
},
"TrainerController.start_learning": {
"total": 411.58153180500005,
"count": 1,
"self": 0.305379094003456,
"children": {
"TrainerController._reset_env": {
"total": 3.4201487279999583,
"count": 1,
"self": 3.4201487279999583
},
"TrainerController.advance": {
"total": 407.76720655099655,
"count": 18192,
"self": 0.32523607599569004,
"children": {
"env_step": {
"total": 287.6026577090046,
"count": 18192,
"self": 219.00698080199004,
"children": {
"SubprocessEnvManager._take_step": {
"total": 68.40079448300048,
"count": 18192,
"self": 1.1880126039831111,
"children": {
"TorchPolicy.evaluate": {
"total": 67.21278187901737,
"count": 18192,
"self": 67.21278187901737
}
}
},
"workers": {
"total": 0.19488242401405387,
"count": 18192,
"self": 0.0,
"children": {
"worker_root": {
"total": 410.17996366400337,
"count": 18192,
"is_parallel": true,
"self": 217.1827917240056,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006089450999979817,
"count": 1,
"is_parallel": true,
"self": 0.004450029999929939,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016394210000498788,
"count": 10,
"is_parallel": true,
"self": 0.0016394210000498788
}
}
},
"UnityEnvironment.step": {
"total": 0.03448357400009172,
"count": 1,
"is_parallel": true,
"self": 0.0005616070001224216,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00040043699993930204,
"count": 1,
"is_parallel": true,
"self": 0.00040043699993930204
},
"communicator.exchange": {
"total": 0.03173933200002921,
"count": 1,
"is_parallel": true,
"self": 0.03173933200002921
},
"steps_from_proto": {
"total": 0.0017821980000007898,
"count": 1,
"is_parallel": true,
"self": 0.0003608350001513827,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.001421362999849407,
"count": 10,
"is_parallel": true,
"self": 0.001421362999849407
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 192.99717193999777,
"count": 18191,
"is_parallel": true,
"self": 9.337604918993861,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.256434822001097,
"count": 18191,
"is_parallel": true,
"self": 5.256434822001097
},
"communicator.exchange": {
"total": 148.54349813299848,
"count": 18191,
"is_parallel": true,
"self": 148.54349813299848
},
"steps_from_proto": {
"total": 29.859634066004332,
"count": 18191,
"is_parallel": true,
"self": 5.235963558014987,
"children": {
"_process_rank_one_or_two_observation": {
"total": 24.623670507989345,
"count": 181910,
"is_parallel": true,
"self": 24.623670507989345
}
}
}
}
}
}
}
}
}
}
},
"trainer_advance": {
"total": 119.83931276599628,
"count": 18192,
"self": 0.38258180400885067,
"children": {
"process_trajectory": {
"total": 25.393800093987807,
"count": 18192,
"self": 24.859799848987564,
"children": {
"RLTrainer._checkpoint": {
"total": 0.534000245000243,
"count": 4,
"self": 0.534000245000243
}
}
},
"_update_policy": {
"total": 94.06293086799963,
"count": 90,
"self": 37.65423353100289,
"children": {
"TorchPPOOptimizer.update": {
"total": 56.40869733699674,
"count": 4587,
"self": 56.40869733699674
}
}
}
}
}
}
},
"trainer_threads": {
"total": 1.0159999419556698e-06,
"count": 1,
"self": 1.0159999419556698e-06
},
"TrainerController._save_models": {
"total": 0.0887964160001502,
"count": 1,
"self": 0.0009471130001657002,
"children": {
"RLTrainer._checkpoint": {
"total": 0.0878493029999845,
"count": 1,
"self": 0.0878493029999845
}
}
}
}
}
}
}