Controlled Markov Decision Processes 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 for possibly unbounded costs.
Keywords: Markov Decision Problem, Average-Value-at-Risk, Optimal Control
Category 1: Applications -- OR and Management Sciences
Citation: University of Washington, November/2016.
Entry Submitted: 11/27/2016
Modify/Update this entry
|Visitors||Authors||More about us||Links|
Search, Browse the Repository
Give us feedback
|Optimization Journals, Sites, Societies|