On a new approach to the analysis of complex multi-armed bandits
R. Garbe and
K. D. Glazebrook
Mathematical Methods of Operations Research, 1998, vol. 48, issue 3, 419-442
Abstract:
A radically new approach to indexable systems pioneered by Bertsimas and Niño-Mora is utilised to provide novel analyses of classes of complex multi-armed bandits in which the individual bandits have their own decision structure. A new index result for an undiscounted model is established. Parallel server versions of the models are studied via (the dual of) an LP relaxation. This analysis yields a natural heuristic policy which is evaluated numerically. Copyright Springer-Verlag Berlin Heidelberg 1998
Keywords: Key words: Conservation laws; Gittins index; LP relaxation; multi-armed bandit; performance space; undiscounted tax problem (search for similar items in EconPapers)
Date: 1998
References: Add references at CitEc
Citations:
Downloads: (external link)
http://hdl.handle.net/10.1007/s001860050036 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:spr:mathme:v:48:y:1998:i:3:p:419-442
Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/00186
DOI: 10.1007/s001860050036
Access Statistics for this article
Mathematical Methods of Operations Research is currently edited by Oliver Stein
More articles in Mathematical Methods of Operations Research from Springer, Gesellschaft für Operations Research (GOR), Nederlands Genootschap voor Besliskunde (NGB)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().