AbstractThis paper studies the class of denumerable-armed (i.e., finite- or countably infinite-armed) Bandit problems with independent arms and geometric discounting over an infinite horizon in which each arm generates rewards according to one of a finite number of distributions. The authors derive certain continuity and curvature properties of the Gittins Index, and provide necessary and sufficient conditions under which this index characterizes the optimal strategies. They then show that at each point in time the arm selected by an optimal strategy will, with positive probability, remain an optimal selection forever. Copyright 1992 by The Econometric Society.
Download InfoTo our knowledge, this item is not available for download. To find whether it is available, there are three options:
1. Check below under "Related research" whether another version of this item is available online.
2. Check on the provider's web page whether it is in fact available.
3. Perform a search for a similarly titled item that would be available.
Bibliographic InfoPaper provided by University of Rochester - Center for Economic Research (RCER) in its series RCER Working Papers with number 277.
Length: 37 pages
Date of creation: 1991
Date of revision:
Contact details of provider:
Postal: University of Rochester, Center for Economic Research, Department of Economics, Harkness 231 Rochester, New York 14627 U.S.A.
mathematics ; probability ; economic models;
Other versions of this item:
You can help add them by filling out this form.
CitEc Project, subscribe to its RSS feed for this item.
- Dirk Bergemann & Juuso Vaimaki, 1999.
"Stationary Multi Choice Bandit Problems,"
Cowles Foundation Discussion Papers
1240, Cowles Foundation for Research in Economics, Yale University.
- Keller, Godfrey & Oldale, Alison, 2003. "Branching bandits: a sequential search process with correlated pay-offs," Journal of Economic Theory, Elsevier, vol. 113(2), pages 302-315, December.
- Bergemann, Dirk & Valimaki, Juuso, 1996.
"Learning and Strategic Pricing,"
Econometric Society, vol. 64(5), pages 1125-49, September.
- Chien-Tai Lin & C. Shiau, 2000. "Some Optimal Strategies for Bandit Problems with Beta Prior Distributions," Annals of the Institute of Statistical Mathematics, Springer, vol. 52(2), pages 397-405, June.
- Araújo, Luis Fernando de Oliveira & Camargo, Braz Ministério de, 2010.
"Monetary equilibrium with decentralized trade and learning,"
Textos para discussÃ£o
222, Escola de Economia de São Paulo, Getulio Vargas Foundation (Brazil).
- Luis Araujo & Braz Camargo, 2005. "Monetary Equilibrium with Decentralized Trade and Learning," UWO Department of Economics Working Papers 20051, University of Western Ontario, Department of Economics.
- Araujo, Luis & Camargo, Braz, 2008. "Endogenous supply of fiat money," Journal of Economic Theory, Elsevier, vol. 142(1), pages 48-72, September.
- Jean Guillaume Forand, 2011.
"Keeping Your Options Open,"
2011 Meeting Papers
82, Society for Economic Dynamics.
- Elena Pastorino, 2004. "Optimal Job Design and Career Dynamics in the Presence of Uncertainty," Econometric Society 2004 North American Summer Meetings 292, Econometric Society.
- Epstein, Gil S., 1996. "The extraction of natural resources from two sites under uncertainty," Economics Letters, Elsevier, vol. 51(3), pages 309-313, June.
- Klimenko, Mikhail M., 2004. "Industrial targeting, experimentation and long-run specialization," Journal of Development Economics, Elsevier, vol. 73(1), pages 75-105, February.
- Kung-Yu Chen & Chien-Tai Lin, 2005. "A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions," Statistical Papers, Springer, vol. 46(1), pages 129-140, January.
- Cripps, Martin W., 2013. "Optimal learning of a set: Or how to edit a journal if you must," Economics Letters, Elsevier, vol. 120(3), pages 384-388.
- Araujo, Luis & Camargo, Braz, 2006. "Information, learning, and the stability of fiat money," Journal of Monetary Economics, Elsevier, vol. 53(7), pages 1571-1591, October.
For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: (Gabriel Mihalache).
If references are entirely missing, you can add them using this form.