Mean and variance responsive learning

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 preferen...

Full description

Saved in:
Bibliographic Details
Published in:Games and economic behavior 2012-07, Vol.75 (2), p.855-866
Main Authors: Oyarzun, Carlos, Sarin, Rajiv
Format: Article
Language:English
Subjects:
Agency theory
Decision making
Decision making models
Expectation
Information economics
Learning
Mean and variance preferences
Pay-off
Payoffs
Preferences
Reinforcement learning
Studies
Variance
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:0899-8256
1090-2473
DOI:10.1016/j.geb.2012.02.013