TY - JOUR
T1 - Mean and variance responsive learning
AU - Oyarzun, C.
AU - Sarin, R.
N1 - Copyright 2012 Elsevier B.V., All rights reserved.
PY - 2012/7/1
Y1 - 2012/7/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?partnerID=yv4JPVwI&eid=2-s2.0-84860620413&md5=e2aac3d18413e120b2ac8e2dda5b720c
U2 - 10.1016/j.geb.2012.02.013
DO - 10.1016/j.geb.2012.02.013
M3 - Article
AN - SCOPUS:84860620413
SN - 0899-8256
VL - 75
SP - 855
EP - 866
JO - Games and Economic Behaviour
JF - Games and Economic Behaviour
IS - 2
ER -