Markov Karar Süreci İle Modellenen Stokastik ve Çok Amaçlı Üretim/Envanter Problemlerinin Hedef Programlama Yaklaşımı İle Çözülmesi (Solving Stochastic and Multi-Objective Production/Inventory Problems Modeled By MARKOV Decision Process with Goal Programming Approach)

Abstract

To make decisions involving uncertainty while making future plans, Markov Decision Process (MDP), one of the stochastic approaches, may provide assistance to managers. Methods such as value iteration, policy iteration or linear programming can be used in the solution of MDPs when only one objective such as profit maximization or cost minimization is considered. However the decisions made by business while operating in a competition environment require considering multiple and usually conflicting objectives simultaneously. Goal programming (GP), can be used to solve such problems. The aim of this study is to provide an integrated perspective involving the utilization of MDP and GP approaches together for the solution of stochastic multi-objective decision problems. To this end the production/inventory system of a business operating in the automotive supplier industry is considered.

Keywords

• Markov Decision Process
• Linear Programming
• Goal Programming
• Multi Objective Markov Decision Process.