Negative Learning Rates and P-Learning. (arXiv:1603.08253v1 [cs.AI])

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.

Donate to arXiv

from cs.AI updates on arXiv.org http://ift.tt/1PBZRc6
via IFTTT