Learning through reinforcement and replicator dynamics
Learning through reinforcement and replicator dynamics
复制标题
DOI：
10.1006/jeth.1997.2319
复制
发表时间：
1997-11-01
影响因子：
1.6
通讯作者：
Sarin, R
中科院分区：
文献类型：
--
作者：
Borgers, T;Sarin, R
本文考虑了R. R. Bush和F. Mosteller's（1951，Psych. Rev. 58. 313-323; 1955，“Stochastic Models for Learning，”Wiley，纽约）游戏背景下的随机学习理论。我们表明，在一个连续的时间限制的学习模型收敛到进化博弈论的复制动力学。因此，我们提供了进化博弈论的非生物学解释。(C)北京：科学出版社.
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.