Learning through reinforcement and replicator dynamics

被引：395

作者：

Borgers, T ^{[1
]}

Sarin, R ^{[1
]}

机构：

[1] TEXAS A&M UNIV,DEPT ECON,COLL LIBERAL ARTS,COLLEGE STN,TX 77843

来源：

JOURNAL OF ECONOMIC THEORY | 1997年 / 77卷 / 01期

基金：

英国经济与社会研究理事会;

关键词：

D O I：

10.1006/jeth.1997.2319

中图分类号：

F [经济];

学科分类号：

02 ;

摘要：

This paper considers a version of R. R. Bush and F. Mosteller's (1951, Psych. Rev. 58. 313-323; 1955, ''Stochastic Models for Learning,'' Wiley, New York) stochastic learning theory in the context of games. We show that in a continuous time limit the learning model converges to the replicator dynamics of evolutionary game theory. Thus we provide a non-biological interpretation of evolutionary game theory. (C) 1997 Academic Press.

引用

页码：1 / 14

页数：14

共 34 条

[1] EVOLUTIONARY DYNAMICS OF ZERO-SUM GAMES [J].

AKIN, E ;

LOSERT, V .

JOURNAL OF MATHEMATICAL BIOLOGY, 1984, 20 (03) :231-258

[2]

BINMORE K, 1993, UNPUB MUDDLING NOISY

[3]

BINMORE K, 1992, FUN GAMES

[4]

BORGERS T, 1995, UNPUB NAIVE REINFORC

[5] CONTINUOUS APPROXIMATION OF DYNAMICAL-SYSTEMS WITH RANDOMLY MATCHED INDIVIDUALS [J].

BOYLAN, RT .

JOURNAL OF ECONOMIC THEORY, 1995, 66 (02) :615-625

[6] LAWS OF LARGE NUMBERS FOR DYNAMIC-SYSTEMS WITH RANDOMLY MATCHED INDIVIDUALS [J].

BOYLAN, RT .

JOURNAL OF ECONOMIC THEORY, 1992, 57 (02) :473-504

[7] A MATHEMATICAL MODEL FOR SIMPLE LEARNING [J].

BUSH, RR ;

MOSTELLER, F .

PSYCHOLOGICAL REVIEW, 1951, 58 (05) :313-323

[8]

BUSH RR, 1955, STOCHASTIC MODELS LE

[9]

CABRALES A, 1993, UNPUB STOCHASTIC REP

[10]

CABRALES A, 1992, J ECON THEORY, V57, P392

← 1 2 3 4 →