Hostname: page-component-7b7567c8c-tnkh4 Total loading time: 0 Render date: 2026-11-17T03:55:18.221Z Has data issue: false hasContentIssue false

Evaluating policies for generalized bandits via a notion of duality

Published online by Cambridge University Press:  14 July 2016

J. H. Crosbie*
Affiliation:
University of Newcastle
K. D. Glazebrook*
Affiliation:
University of Newcastle
*
∗ Postal address: Department of Statistics, University of Newcastle, Newcastle upon Tyne NE1 7RU, UK
∗ Postal address: Department of Statistics, University of Newcastle, Newcastle upon Tyne NE1 7RU, UK

Abstract

Nash's generalization of Gittins’ classic index result to so-called generalized bandit problems (GBPs) in which returns are dependent on the states of all arms (not only the one which is pulled) has proved important for applications. The index theory for special cases of this model in which all indices are positive is straightforward. However, this is not a natural restriction in practice. An earlier proposal for the general case did not yield satisfactory index-based suboptimality bounds for policies — a central feature of classical Gittins index theory. We develop such bounds via a notion of duality for GBPs which is of independent interest. The index which emerges naturally from this analysis is the reciprocal of the one proposed by Nash.

Information

Type
Research Papers
Copyright
Copyright © by the Applied Probability Trust 2000 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable