On the nonconvergence of fictitious play in coordination games

被引：33

作者：

Foster, DP ^{[1
]}

Young, HP

机构：

[1] Univ Penn, Wharton Sch, Dept Stat, Philadelphia, PA 19104 USA

[2] Johns Hopkins Univ, Dept Econ, Baltimore, MD 21218 USA

来源：

GAMES AND ECONOMIC BEHAVIOR | 1998年 / 25卷 / 01期

基金：

美国国家科学基金会;

关键词：

fictitious play; coordination game; learning; cycles; Shapley example;

D O I：

10.1006/game.1997.0626

中图分类号：

F [经济];

学科分类号：

02 [经济学];

摘要：

It is shown by example that learning rules of the fictitious play type fail to converge in certain kinds of coordination games. Variants of fictitious play in which past actions are eventually forgotten and that incorporate small stochastic perturbations are better behaved for this class of games: over the long run, players coordinate with probability one. Classification Numbers: C70, C72. (C) 1998 Academic Press.

引用

页码：79 / 96

页数：18

共 13 条

[1]

BENAIM M, 1996, UNPUB LEARNING PROCE

[2]

LEARNING MIXED EQUILIBRIA [J].

FUDENBERG, D ;

KREPS, DM .

GAMES AND ECONOMIC BEHAVIOR, 1993, 5 (03) :320-367

[3]

LEARNING, MUTATION, AND LONG-RUN EQUILIBRIA IN GAMES [J].

KANDORI, M ;

MAILATH, GJ ;

ROB, R .

ECONOMETRICA, 1993, 61 (01) :29-56

[4]

LEARNING DYNAMICS IN GAMES WITH STOCHASTIC PERTURBATIONS [J].

KANIOVSKI, YM ;

YOUNG, HP .

GAMES AND ECONOMIC BEHAVIOR, 1995, 11 (02) :330-363

[5]

KRISHNA V, 1992, UNPUB LEARNING GAMES

[6]

KRISHNA V, 1997, UNPUB CONVERGENCE FI

[7]

ADAPTIVE AND SOPHISTICATED LEARNING IN NORMAL-FORM GAMES [J].

MILGROM, P ;

ROBERTS, J .

GAMES AND ECONOMIC BEHAVIOR, 1991, 3 (01) :82-100

[8]

MIYASAWA K, 1961, 33 PRINCT U EC RES P

[9]

Fictitious play property for games with identical interests [J].

Monderer, D ;

Shapley, LS .

JOURNAL OF ECONOMIC THEORY, 1996, 68 (01) :258-265

[10]

Potential games [J].

Monderer, D ;

Shapley, LS .

GAMES AND ECONOMIC BEHAVIOR, 1996, 14 (01) :124-143

← 1 2 →