Controlled Markov Decision Processes with AVaR Criteria for Unbounded Costs

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 for possibly unbounded costs.

Citation

University of Washington, November/2016.

Article

Download

View Controlled Markov Decision Processes with AVaR Criteria for Unbounded Costs