Generalized Bandit Problems

Rangarajan K. Sundaram ()
Additional contact information
Rangarajan K. Sundaram: New York University

A chapter in Social Choice and Strategic Decisions, 2005, pp 131-162 from Springer

Abstract: Summary This chapter examines a number of extensions of the multi-armed bandit framework. We consider the possibility of an infinite number of available arms, we give conditions under which the Gittins index strategy is well-defined, and we examine the optimality of that strategy. We then consider some difficulties arising from “parallel search,” in which a decision-maker may pull more than one arm per period, and from the introduction of a cost of switching between arms.

Keywords: Optimal Strategy; Switching Cost; Index Strategy; Bandit Problem; Dynamic Programming Problem (search for similar items in EconPapers)
Date: 2005
References: Add references at CitEc
Citations: View citations in EconPapers (2)

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

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:stcchp:978-3-540-27295-3_6

Ordering information: This item can be ordered from
http://www.springer.com/9783540272953

DOI: 10.1007/3-540-27295-X_6

Access Statistics for this chapter

More chapters in Studies in Choice and Welfare from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().