Risk preferences of learning algorithms

Andreas Haupt and Aroon Narayanan

Games and Economic Behavior, 2024, vol. 148, issue C, 415-426

Abstract: Many economic decision-makers today rely on learning algorithms for important decisions. This paper shows that a widely used learning algorithm—ε-Greedy—exhibits emergent risk aversion, favoring actions with lower payoff variance. When presented with actions of the same expectated payoff, under a wide range of conditions, ε-Greedy chooses the lower-variance action with probability approaching one. This emergent preference can have wide-ranging consequences, from inequity to homogenization, and holds transiently even when the higher-variance action has a strictly higher expected payoff. We discuss two methods to restore risk neutrality. The first method reweights data as a function of how likely an action is chosen. The second method employs optimistic payoff estimates for actions that have not been taken often.

Keywords: Online learning; Behavior attribution; Fairness (search for similar items in EconPapers)
Date: 2024
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S089982562400143X
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:gamebe:v:148:y:2024:i:c:p:415-426

DOI: 10.1016/j.geb.2024.09.013

Access Statistics for this article

Games and Economic Behavior is currently edited by E. Kalai

More articles in Games and Economic Behavior from Elsevier
Bibliographic data for series maintained by Catherine Liu ().