期刊名称：Journal of International Technology and Information Management
印刷版ISSN：1941-6679
出版年度：2019
卷号：28
期号：3
页码：67-90
出版社：California State University, San Bernardino
摘要：With the increase in the complexity of supply chain management, the use of intelligent agents for automated trading has gained popularity (Collins, Arunachalam, B, et al. 2006). The performance of supply-chain agents depends on not just the market environment (supply and demand patterns) but also on what types of other agents they are competing with. For designers of such agents it is important to ascertain that their agents are robust and can adapt to changing market and competitive environments. However, to date there has not been any work done that assesses the adaptability of a trading agent’s strategy in the presence of various demand and supply distributions when competing with a changing composition of agents using different strategies. In this paper we use the concept of replicator dynamics to study the evolution of a population of strategies used by supply chain agents when the different agents are competing against each other. We also study the evolution of the population of agents’ strategies in the presence of six types of adverse market conditions. In particular we test three strategies that have been presented in the literature and our results indicate that over time supply chain agents gravitate towards using the SCMaster strategy in most scenarios.
关键词：multi-agent systems; reinforcement learning; replicator dynamics; artificial intelligence; e-commerce; simulation; supply chain management; evolutionary game theory
