Optimal Activation of Halting Multi-Armed Bandit Models
Machine Learning
2023-04-21 v1 Machine Learning
Abstract
We study new types of dynamic allocation problems the {\sl Halting Bandit} models. As an application, we obtain new proofs for the classic Gittins index decomposition result and recent results of the authors in `Multi-armed bandits under general depreciation and commitment.'
Cite
@article{arxiv.2304.10302,
title = {Optimal Activation of Halting Multi-Armed Bandit Models},
author = {Wesley Cowan and Michael N. Katehakis and Sheldon M. Ross},
journal= {arXiv preprint arXiv:2304.10302},
year = {2023}
}