POLYNOMIALLY BOUNDED RATIONALITY
成果类型：
Article
署名作者：
BOARD, R
刊物名称：
JOURNAL OF ECONOMIC THEORY
ISSN/ISSBN：
0022-0531
DOI：
10.1006/jeth.1994.1042
发表日期：
1994
页码：
246-270
关键词：
摘要：
This paper explores the conditions under which agents can learn enough about an economy to form rational expectations. The agents' rationality is bounded by limiting their computational resources to algorithms with running time bounded by a polynomial in the relevant problem parameters. We characterize the classes of price functions and economies that agents can learn under these assumptions and present a result that suggests that it is unlikely that agents can learn even those price functions and economies computable by finite state automata. This result casts doubt on the ability of agents to form rational expectations in complex economies. (C) 1994 Academic Press, inc.
来源URL：