AUTHOR=Loecher Markus 

TITLE=The Perils of Misspecified Priors and Optional Stopping in Multi-Armed Bandits

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=4

YEAR=2021

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2021.715690

DOI=10.3389/frai.2021.715690

ISSN=2624-8212

ABSTRACT=<p>The connection between optimal stopping times of American Options and multi-armed bandits is the subject of active research. This article investigates the effects of optional stopping in a particular class of multi-armed bandit experiments, which randomly allocates observations to arms proportional to the Bayesian posterior probability that each arm is optimal (<italic>Thompson sampling</italic>). The interplay between optional stopping and prior mismatch is examined. We propose a novel partitioning of regret into peri/post testing. We further show a strong dependence of the parameters of interest on the assumed prior probability density.</p>