INDEPENDENTLY EXPIRING MULTIARMED BANDITS

Authors
RIGHTER R SHANTHIKUMAR JG
Citation
R. Righter et Jg. Shanthikumar, INDEPENDENTLY EXPIRING MULTIARMED BANDITS, Probability in the engineering and informational sciences, 12(4), 1998, pp. 453-468
Citations number
14
Categorie Soggetti
Statistic & Probability","Operatione Research & Management Science","Engineering, Industrial","Statistic & Probability","Operatione Research & Management Science
Journal title
Probability in the engineering and informational sciences → ACNP
ISSN journal
02699648
Volume
12
Issue
4
Year of publication
1998
Pages
453 - 468
Database
ISI
SICI code
0269-9648(1998)12:4<453:IEMB>2.0.ZU;2-P
Abstract
We give conditions on the optimality of an index policy for multiarmed bandits when arms expire independently. We also give a new simple pro of of the optimality of the Gittins index policy for the classic multi armed bandit problem.