Open Access
January, 1990 Randomization in the Two-Armed Bandit Problem
Robert C. Dalang
Ann. Probab. 18(1): 218-225 (January, 1990). DOI: 10.1214/aop/1176990946

Abstract

We give a short new proof of the existence of optimal solutions to a continuous time formulation of the two-armed bandit problem, using a new topological embedding of the set of randomized optional increasing paths. We do not make any hypothesis on the two-parameter filtration, other than completeness and right-continuity.

Citation

Download Citation

Robert C. Dalang. "Randomization in the Two-Armed Bandit Problem." Ann. Probab. 18 (1) 218 - 225, January, 1990. https://doi.org/10.1214/aop/1176990946

Information

Published: January, 1990
First available in Project Euclid: 19 April 2007

zbMATH: 0713.60054
MathSciNet: MR1043945
Digital Object Identifier: 10.1214/aop/1176990946

Subjects:
Primary: 60G40
Secondary: 93E20

Keywords: Randomization , Stochastic control , two-armed bandit , two-parameter process

Rights: Copyright © 1990 Institute of Mathematical Statistics

Vol.18 • No. 1 • January, 1990
Back to Top