Abstract
dc:description.abstractThis thesis consists of three interrelated chapters on adaptive learning. In each chapter, I investigate the way in which adaptive decision makers/players behave in the long run. In particular, I consider subjective assessment maximizers; each player assigns a subjective assessment to each of his actions based on its past performance and chooses the action which has the highest assessment. They update their assessments adaptively using realized payoffs. I mainly focus on the following three cases; (1) an adaptive decision maker takes into account not only direct payoff information, but also foregone payoff information; (2) adaptive players face a normal form game with strict Nash equilibrium in each of infinitely many periods; and (3) adaptive players face a finitely repeated game in each of infinitely iterated periods. Then I show the conditions under which (1) adaptive decision maker chooses the optimal action, (2) adaptive players end up choosing Nash equilibrium strategies, and (3) adaptive players’ behavioural strategies converge to an agent quantal response equilibrium, which is a quantal response equilibrium for extensive form games.
Degree
thesis:*- Name dc:type.qualificationname
- d_ph
- Level dc:type.qualificationlevel
- d_ph
- Grantor dc:publisher.institution
- University of Birmingham
- Year dc:date.issued
- 2013
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Funai, Naoki
Subjects
dc:subject × 1Rights
- Language dc:language.dcterms_iso639_2
- eng