不完全博弈学习过程的虚拟行动规则  

Rule of Fictitious Play in the Learning Process with Incomplete Learning Times

作　　者：丁占文[1] 蔡超英[1] 杨宏林[1] 蒋书敏[1] 

机构地区：[1]江苏大学理学院,镇江212013

出　　处：《运筹学学报》2010年第3期91-100,共10页Operations Research Transactions

基　　金：江苏省高校哲学社会科学重点研究基地重大招标项目(2010-2-8);江苏大学高级人才基金(08JDG053;09JDG073)

摘　　要：本文把博弈学习虚拟行动规则的学习时间一般化,研究不完全学习过程中参与人策略选择的收敛性及效用一致性问题.分析结果表明:当学习时间不完全时,在学习一致到达的条件下,虚拟行动规则对严格纳什均衡是吸收的;在学习时间充分及时与虚拟行动非频繁转换的条件下,各参与人的虚拟行动具有效用一致性.In this paper we have generalized the time frequency of learning in the repeated games to study the problems of strategy converging and utility consistency under the fictitious play rule.We have showed that in the process of incomplete learning,the strict Nash Equilibria are absorbing for the fictitious play provided they are played by uniform learning and the fictitious play has the property of utility consistency when the learning times are frequent enough and the fictitious play exhibits infrequent switches.

关 键 词：运筹学 博弈 虚拟行动 不完全学习 

分 类 号：O157.5[理学—数学]