基于影响图的多Agent决策问题研究  

Study of the decision problem of multi-agent systems based on IDs

作　　者：王浩[1] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2005年第9期1112-1116,共5页Journal of Hefei University of Technology：Natural Science

基　　金：安徽省自然科学基金资助项目(03042305)

摘　　要：影响图是决策问题的图形表示,它是在贝叶斯网络基础上增加了决策结点和效用结点。文章讨论了影响图理论在多Agent建模与决策方面的应用;提出了联合分层影响图和动态贝叶斯网络来实现多Agent的实时决策的方法,该方法已在Robcup球员建模和决策方面初步得到应用。Influence Diagrams （IDs） are graphical knowledge representation of decision problems and can be viewed as an extension of Bayesian Networks （BNs） with additional node types for decision and utility. In this paper ,the application of Influence Diagrams in modeling and decision making of multiagent systems is discussed. The method that combines hierarchical Influence Diagrams and Dynamic Bayesian Networks to process real-time decision problems of agents is presented ,and it is applied to decision-making in Robocup Simulation Contest.

关 键 词：影响图 贝叶斯网络 多AGENT系统 决策 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]