The Annals of Applied Probability

A Short Proof of the Gittins Index Theorem

John N. Tsitsiklis
Source: Ann. Appl. Probab. Volume 4, Number 1 (1994), 194-199.

Abstract

We provide a short and elementary proof of the Gittins index theorem for the multi-armed bandit problem, for the case where each bandit is modeled as a finite-state semi-Markov process. We also indicate how this proof can be extended to the branching bandits and Klimov problems.

First Page: Show Hide
Primary Subjects: 60G40
Secondary Subjects: 90B35, 62L05, 90C40
Full-text: Open access
Links and Identifiers

Permanent link to this document: http://projecteuclid.org/euclid.aoap/1177005207
JSTOR: links.jstor.org
Digital Object Identifier: doi:10.1214/aoap/1177005207
Mathematical Reviews number (MathSciNet): MR1258180
Zentralblatt MATH identifier: 0816.60040


2013 © Institute of Mathematical Statistics

The Annals of Applied Probability

The Annals of Applied Probability

Turn MathJax Off
What is MathJax?