Mean and variance responsive learning

Oyarzun, Carlos and Sarin, Rajiv (2012) Mean and variance responsive learning. Games and Economic Behavior, 75 2: 855-866. doi:10.1016/j.geb.2012.02.013

Author Oyarzun, Carlos
Sarin, Rajiv
Title Mean and variance responsive learning
Journal name Games and Economic Behavior   Check publisher's open access policy
ISSN 0899-8256
Publication date 2012-04-01
Sub-type Article (original research)
DOI 10.1016/j.geb.2012.02.013
Open Access Status Not yet assessed
Volume 75
Issue 2
Start page 855
End page 866
Total pages 12
Place of publication Maryland Heights, MO, U.S.A.
Publisher Academic Press
Language eng
Formatted abstract
Decision makers are often described as seeking higher expected payoffs and avoiding higher variance in payoffs. We provide some necessary and some sufficient conditions for learning rules, that assume the agent has little prior and feedback information about the environment, to reflect such preferences. We adopt the framework of Börgers, Morales and Sarin (2004, Econometrica) who provide similar results for learning rules that seek higher expected payoffs. Our analysis reveals that a concern for variance leads to quadratic transformations of payoffs to appear in the learning rule.
Keyword Learning
Reinforcement learning
Mean and variance preferences
Q-Index Code C1
Q-Index Status Confirmed Code
Institutional Status UQ

Document type: Journal Article
Sub-type: Article (original research)
Collections: Official 2013 Collection
School of Economics Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 1 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 17 Apr 2012, 01:50:00 EST by Alys Hohnen on behalf of School of Economics