A central limit theorem, loss aversion and multi-armed bandits

This paper studies a multi-armed bandit problem where the decision-maker is loss averse, in particular she is risk averse in the domain of gains and risk loving in the domain of losses. The focus is on large horizons. Consequences of loss aversion for asymptotic (large horizon) properties are derive...

Full description

Saved in:
Bibliographic Details
Published inJournal of economic theory Vol. 209; p. 105645
Main Authors Chen, Zengjing, Epstein, Larry G., Zhang, Guodong
Format Journal Article
LanguageEnglish
Published Elsevier Inc 01.04.2023
Subjects
Central limit theorem
Large-horizon approximations
Loss aversion
Multi-armed bandit
Oscillating Brownian motion
Sequential sampling
Central limit theorem
Sequential sampling
Large-horizon approximations
Oscillating Brownian motion
D81
D91
D83
Multi-armed bandit
Loss aversion
Online AccessGet full text

Cover

More Information
Summary:This paper studies a multi-armed bandit problem where the decision-maker is loss averse, in particular she is risk averse in the domain of gains and risk loving in the domain of losses. The focus is on large horizons. Consequences of loss aversion for asymptotic (large horizon) properties are derived in a number of analytical results. The analysis is based on a new central limit theorem for a set of measures under which conditional variances can vary in a largely unstructured history-dependent way subject only to the restriction that they lie in a fixed interval.
ISSN:0022-0531
1095-7235
DOI:10.1016/j.jet.2023.105645