Convex function approximations for Markov decision processes

Abstract

This paper studies function approximation for finite horizon discrete time Markov decision processes under certain convexity assumptions. Uniform convergence of these approximations on compact sets is proved under several sampling schemes for the driving random variables. Under some conditions, these approximations form a monotone sequence of lower or upper bounding functions. Numerical experiments involving piecewise linear functions demonstrate that very tight bounding functions for the fair price of a Bermudan put option can be obtained with excellent speed (fractions of a cpu second). Results in this paper can be easily adapted to minimization problems involving concave Bellman functions.