Negative Learning Rates and P-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.

arXiv commentEmbarrassingly poor manuscript with many errors

Cited by in corpus (1)

• DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future