A convergent recursive least squares approximate policy iteration algorithm for multi-dimensional Markov decision process with continuous state and action spaces

Abstract

In this paper, we present a recursive least squares approximate policy iteration (RLSAPI) algorithm for infinite-horizon multi-dimensional Markov decision process in continuous state and action spaces. Under certain problem structure assumptions on value functions and policy spaces, the approximate policy iteration algorithm is provably convergent in the mean. That is to say the mean absolute deviation of the approximate policy value function from the optimal value function goes to zero as successive approximation improves.