一种基于多agent学习的电子市场智能定价方法  

Pricing in marketplaces by multiagent learning

作　　者：韩伟[1] 王云[1] 吕捷[1] 

机构地区：[1]南京财经大学信息工程学院,南京210046

出　　处：《计算机工程与应用》2007年第15期208-211,共4页Computer Engineering and Applications

基　　金：江苏省教育厅"青蓝工程"优秀青年骨干教师计划。

摘　　要：B2B电子市场的定价问题是一个半学习半推理的连续决策过程,每个定价agent不是直接采用多agent学习算法下的均衡策略,而是根据博弈历史进行推理决策,并不断学习对手的策略。提出了基于内省推理方法的多agent环境下agent高效在线学习方法,将基于对手模型的客观观察行为与基于换位思考推理的主观意图推测结合起来。仿真结果证实了算法在电子市场定价中的有效性。The pricing problem in B2B electronic marketplaces is a continuous decision process,which can be seen as learning as well as inference.In stead of adopting the equilibrium policy,each pricing agent makes a decision by the pricing history of all agents.This paper proposes an efficient online learning algorithm,which integrates the observed objective behavior as well as the subjective inferential intention of the opponents,The algorithm is proven to be effective when it comes to the problem of seller＇s pricing in electronic market.

关 键 词：多AGENT系统 在线学习 内省推理 电子市场 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]