Affiliation:
1. Computer Science Department Rutgers University Piscataway New Jersey USA
2. Management Science and Information Systems Department Rutgers University Piscataway New Jersey USA
3. Systems Engineering Department University of Southern California Los Angeles California USA
Abstract
AbstractWe study new types of dynamic allocation problems the Halting Bandit models. As an application, we obtain new proofs for the classic Gittins index decomposition result compare Gittins (Journal of the Royal Statistical Society, Series B, 1979, 41, 148–177), and recent results of the authors in Cowan and Katehakis (Probability in the Engineering and Informational Sciences, 2015, 29, 51–76).
Funder
National Science Foundation
Subject
Management Science and Operations Research,Ocean Engineering,Modeling and Simulation
Reference34 articles.
1. A stochastic representation theorem with applications to optimization and obstacle problems
2. Multi‐armed bandits, Gittins index, and its calculation;Chakravorty J.;Methods and Applications of Statistics in Clinical Trials,2014
3. MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
4. Normal bandits of unknown means and variances;Cowan W.;Journal of Machine Learning Research,2018
5. Risk-Sensitive and Risk-Neutral Multiarmed Bandits