Stable Dual Dynamic Programming
Tao Wang, Daniel Lizotte, Michael Bowling, Dale Schuurmans · 2008
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. 1