Lancaster EPrints

Discounted multi-armed bandit problems on a collection of machines with varying speeds

Glazebrook, Kevin and Dunn, R. T. (2004) Discounted multi-armed bandit problems on a collection of machines with varying speeds. Mathematics of Operations Research, 29 (2). pp. 266-279. ISSN 1526-5471

Full text not available from this repository.

Abstract

This paper is the first to consider general multiarmed bandit problems on parallel machines working at different speeds. Block allocation policies make a once-for-all allocation of bandits to machines at time zero. In this class we describe how to achieve Blackwell optimality under given conditions. The block allocation policy identified allocates the bandits with the largest guaranteed reward rates to the machines operating at greatest speed. This policy is shown to be average-reward optimal in the class of general (nonanticipative, nonidling) policies.

Item Type: Article
Journal or Publication Title: Mathematics of Operations Research
Additional Information: RAE_import_type : Journal article RAE_uoa_type : Statistics and Operational Research
Uncontrolled Keywords: average reward optimality ; Blackwell optimality ; Gittins index ; multiarmed bandit ; sensitive discount optimality
Subjects: Q Science > QA Mathematics
Departments: Faculty of Science and Technology > Mathematics and Statistics
ID Code: 2424
Deposited By: ep_importer
Deposited On: 31 Mar 2008 13:08
Refereed?: Yes
Published?: Published
Last Modified: 25 Mar 2013 15:10
Identification Number:
URI: http://eprints.lancs.ac.uk/id/eprint/2424

Actions (login required)

View Item