A Central Limit Theorem, Loss Aversion and Multi-Armed Bandits
Probability
2022-05-19 v2 Machine Learning
Theoretical Economics
Machine Learning
Abstract
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.
Keywords
Cite
@article{arxiv.2106.05472,
title = {A Central Limit Theorem, Loss Aversion and Multi-Armed Bandits},
author = {Zengjing Chen and Larry G. Epstein and Guodong Zhang},
journal= {arXiv preprint arXiv:2106.05472},
year = {2022}
}