Saved in:
Bibliographic Details
Main Authors: Veroutis, Peter, Godin, Frédéric
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.16486
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916468246970368
author Veroutis, Peter
Godin, Frédéric
author_facet Veroutis, Peter
Godin, Frédéric
contents The Multiarmed Bandits (MAB) problem has been extensively studied and has seen many practical applications in a variety of fields. The Survival Multiarmed Bandits (S-MAB) open problem is an extension which constrains an agent to a budget that is directly related to observed rewards. As budget depletion leads to ruin, an agent's objective is to both maximize expected cumulative rewards and minimize the probability of ruin. This paper presents a framework that addresses such a dual goal using an objective function balanced by a ruin aversion component. Action values are estimated through a novel approach which consists of bootstrapping samples from previously observed rewards. In numerical experiments, the policies we present outperform benchmarks from the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2410_16486
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Survival Multiarmed Bandits with Bootstrapping Methods
Veroutis, Peter
Godin, Frédéric
Machine Learning
The Multiarmed Bandits (MAB) problem has been extensively studied and has seen many practical applications in a variety of fields. The Survival Multiarmed Bandits (S-MAB) open problem is an extension which constrains an agent to a budget that is directly related to observed rewards. As budget depletion leads to ruin, an agent's objective is to both maximize expected cumulative rewards and minimize the probability of ruin. This paper presents a framework that addresses such a dual goal using an objective function balanced by a ruin aversion component. Action values are estimated through a novel approach which consists of bootstrapping samples from previously observed rewards. In numerical experiments, the policies we present outperform benchmarks from the literature.
title Survival Multiarmed Bandits with Bootstrapping Methods
topic Machine Learning
url https://arxiv.org/abs/2410.16486