Maximizing the length of a success run for many-armed bandits

Donald A. Berry and Bert Fristedt

Stochastic Processes and their Applications, 1983, vol. 15, issue 3, 317-325

Abstract: One of a number of Bernoulli processes is selected at each of a number of stages. A success at stage i is worth [alpha]i and the problem is to maximize the expected payoff before the first failure. Results of Berry and Viscusi (1981) are generalized. In particular, we show that there is always an optimal strategy that uses a single process exclusively and indefinitely whenever the arms are independent and the discount sequence ([alpha]1, [alpha]2,...) is superregular. There is not always a similar reduction in the number of strategies when the discount sequence is not superregular.

Keywords: Many-armed; bandits; sequential; decisions; gambling; with; discounting; Bernoulli; processes; single-arm; strategies; stay-on-a-winner; rule (search for similar items in EconPapers)
Date: 1983
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/0304-4149(83)90039-X
Full text for ScienceDirect subscribers only

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:eee:spapps:v:15:y:1983:i:3:p:317-325

Ordering information: This journal article can be ordered from
http://http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
https://shop.elsevie ... _01_ooc_1&version=01

Access Statistics for this article

Stochastic Processes and their Applications is currently edited by T. Mikosch

More articles in Stochastic Processes and their Applications from Elsevier
Bibliographic data for series maintained by Catherine Liu ().