Diffusion Approximation for Bayesian Markov Chains

Abstract

Given a Markov chain with uncertain transition probabilities modelled in a Bayesian way, we investigate a technique for analytically approximating the mean transition frequency counts over a finite horizon. Conventional techniques for addressing this problem either require the enumeration of a set of generalized process "hyperstates" whose cardinality grows exponentially with the terminal horizon, or axe limited to the two-state case and expressed in terms of hypergeometric series. Our approach makes use of a diffusion approximation technique for modelling the evolution of information state components of the hyperstate process. Interest in this problem stems from a consideration of the policy evaluation step of policy iteration algorithms applied to Markov decision processes with uncertain transition probabilities. ICML Proceedings of the Twentieth International Conference on Machine Learning