Optimal control of infinite horizon partially observable decision processes modelled as generators of probabilistic regular languages

Author： Chattopadhyay Ishanu Ray Asok

Publisher： Taylor & Francis Ltd

ISSN： 1366-5820

Source： International Journal of Control, Vol.83, Iss.3, 2010-03, pp. : 457-483

Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.

Previous Menu Next

Abstract

Decision processes with incomplete state feedback have been traditionally modelled as partially observable Markov decision processes. In this article, we present an alternative formulation based on probabilistic regular languages. The proposed approach generalises the recently reported work on language measure theoretic optimal control for perfectly observable situations and shows that such a framework is far more computationally tractable to the classical alternative. In particular, we show that the infinite horizon decision problem under partial observation, modelled in the proposed framework, is λ-approximable and, in general, is not harder to solve compared to the fully observable case. The approach is illustrated via two simple examples.