Stationary multi-choice bandit problems
Stationary multi-choice bandit problems
This note shows that the optimal choice of k simultaneous experiments in a stationary multi-armed bandit problem can be characterized in terms of the Gittins index of each arm. The index characterization remains equally valid after the introduction of switching costs.
multi-armed bandits, Gittins index, stationary bandits, job search
1585-1594
Bergemann, Dirk
436929ea-1d3f-48d5-bf4f-08ef4a2d74b4
Valimaki, Juuso
6cb468e1-96a7-4632-8db2-906714498ce2
2001
Bergemann, Dirk
436929ea-1d3f-48d5-bf4f-08ef4a2d74b4
Valimaki, Juuso
6cb468e1-96a7-4632-8db2-906714498ce2
Bergemann, Dirk and Valimaki, Juuso
(2001)
Stationary multi-choice bandit problems.
Journal of Economic Dynamics and Control, 25 (10), .
(doi:10.1016/S0165-1889(99)00064-0).
Abstract
This note shows that the optimal choice of k simultaneous experiments in a stationary multi-armed bandit problem can be characterized in terms of the Gittins index of each arm. The index characterization remains equally valid after the introduction of switching costs.
This record has no associated files available for download.
More information
Published date: 2001
Keywords:
multi-armed bandits, Gittins index, stationary bandits, job search
Identifiers
Local EPrints ID: 33055
URI: http://eprints.soton.ac.uk/id/eprint/33055
ISSN: 0165-1889
PURE UUID: b1429343-eb1b-4dc0-8832-65f908c01234
Catalogue record
Date deposited: 15 May 2006
Last modified: 15 Mar 2024 07:41
Export record
Altmetrics
Contributors
Author:
Dirk Bergemann
Author:
Juuso Valimaki
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics