Stable Dual Dynamic Programming

Recently, we have introduced a novel approach to dynamic programming and reinforcement learning that is based on maintaining explicit representations of stationary distributions instead of value functions. In this paper, we investigate the convergence properties of these dual algorithms both theoretically and empirically, and show how they can be scaled up by incorporating function approximation.

• Type: Conference
• Year: 2007
• Where: NIPS
• Authors: Tao Wang, Daniel J. Lizotte, Michael H. Bowling, Dale Schuurmans
• Keywords: Dynamic Programming, Explicit Representations, Information Technology, NIPS 2007, Stationary Distributions