Essays on adaptive learning

[摘要] This thesis consists of three interrelated chapters on adaptive learning. In each chapter, I investigate the way in which adaptive decision makers/playersbehave in the long run. Inparticular, I consider subjective assessment maximizers;each player assigns a subjectiveassessment to each of his actions based on its past performance and chooses the action which hasthe highest assessment. They update their assessments adaptively using realized payoffs. I mainlyfocus on the following three cases; (1) an adaptive decision maker takes into account not only direct payoff information, but also foregone payoff information; (2) adaptiveplayers face anormal form game with strict Nash equilibrium in each of infinitely many periods; and (3) adaptiveplayers face a finitely repeated game in each of infinitely iterated periods. Then I show theconditions under which (1) adaptive decision maker chooses the optimal action, (2) adaptive playersend up choosing Nash equilibrium strategies, and (3) adaptive players’ behaviouralstrategiesconverge to an agent quantal response equilibrium, which is a quantal response equilibrium for extensive form games.

[发布机构] University:University of Birmingham;Department:Birmingham Business School, Department of Economics

[关键词] H Social Sciences;HB Economic Theory