Increasing the Action Gap: New Operators for Reinforcement Learning

15 Dec 2015Marc G. BellemareGeorg OstrovskiArthur GuezPhilip S. ThomasRémi Munos

This paper introduces new optimality-preserving operators on Q-functions. We first describe an operator for tabular representations, the consistent Bellman operator, which incorporates a notion of local policy consistency... (read more)

PDF Abstract

Evaluation results from the paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.