Negative Learning Rates and P-Learning
Artificial Intelligence
2018-06-19 v3 Machine Learning
Abstract
We present a method of training a differentiable function approximator for a regression task using negative examples. We effect this training using negative learning rates. We also show how this method can be used to perform direct policy learning in a reinforcement learning setting.
Cite
@article{arxiv.1603.08253,
title = {Negative Learning Rates and P-Learning},
author = {Devon Merrill},
journal= {arXiv preprint arXiv:1603.08253},
year = {2018}
}
Comments
Embarrassingly poor manuscript with many errors