Optimization Online


Controlled Markov Chains with AVaR Criteria for Unbounded Costs

Kerem Ugurlu (kugurlu***at***usc.edu)

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.

Keywords: Markov Decision Problem, Average-Value-at-Risk, Optimal Control

Category 1: Applications -- OR and Management Sciences


Download: [PDF]

Entry Submitted: 09/27/2015
Entry Accepted: 09/27/2015
Entry Last Modified: 03/29/2016

Modify/Update this entry

  Visitors Authors More about us Links
  Subscribe, Unsubscribe
Digest Archive
Search, Browse the Repository


Coordinator's Board
Classification Scheme
Give us feedback
Optimization Journals, Sites, Societies
Mathematical Optimization Society