A simulation-based approach to study stochastic inventory-planning games

Abstract

Non-cooperative decision-making problems in a decentralized supply chain can be characterized and studied using a stochastic game model. In an earlier paper, the authors developed a methodology that uses machine learning for finding (near) optimal policies for non-zero sum stochastic games, and applied their methodology on an N-retailer and W-warehouse inventory-planning problem. The focus of this paper is on making the methodology more amenable to practical applications by making it completely simulation-based. It is also demonstrated, through numerical example problems, how this methodology can be used to find (near) equilibrium policies, and evaluate short-term rewards of stochastic games. Short-term rewards of stochastic games could be, in many instances, more critical than equilibrium rewards. To our knowledge, no methodology exists in the open literature that can capture the short-term behaviour of non-zero sum stochastic games as examined in this paper.