Controlled Markov Chains with AVaR Criteria for Unbounded Costs

Abstract

In this paper, we consider the control problem with the Average-Value-at-Risk (AVaR) criteria of the possibly unbounded $L^{1}$-costs in infinite horizon on a Markov Decision Process (MDP). With a suitable state aggregation and by choosing a priori a global variable $s$ heuristically, we show that there exist optimal policies for the infinite horizon problem. To our knowledge, this is the first work of deriving dynamic programming equations with $L^1$-unbounded costs via AVaR-operator.