Case-based learning with different similarity functions

• 成果类型: Article
• 署名作者: Guerdjikova, Ani
• 署名单位: Cornell University
• 刊物名称: GAMES AND ECONOMIC BEHAVIOR
• ISSN/ISSBN: 0899-8256
• DOI: 10.1016/j.geb.2007.10.004
• 发表日期: 2008
• 页码: 107-132
• 关键词: Case-based decision theory; Similarity; optimal behavior

摘要

The paper applies the rule for adaptation of the aspiration level suggested by Gilboa and Schmeidler to a situation in which the similarity between acts is represented by an arbitrary similarity function [Gilboa, I., Schmeidler, D., 1996. Case-based optimization. Games Econ. Behav. 15, 1-26]. I show that the optimality result derived by Gilboa and Schmeidler in general fails. With a concave similarity function, only corner acts are chosen in the limit. The optimality result can tie reestablished by introducing convex regions into the similarity function and modifying the aspiration adaptation rule. A similarity function which is sufficiently convex allows approximating optimal behavior with an arbitrary degree of precision. (c) 2007 Elsevier Inc. All rights reserved.