Negative Learning Rates and P-Learning

2016-03-27Unverified0· sign in to hype

Devon Merrill

Unverified — Be the first to reproduce this paper.

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.

Tasks

regression reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Negative Learning Rates and P-Learning

Abstract

Tasks

Reproductions