Gambling in a rigged casino: the adversarial multi-armed bandit problem

by: Peter Auer, Nicolò C Bianchi, Yoav Freund, Robert E Schapire

(1995), pp. 322-331.

View FullText article

CiteSeer (at Penn State), CiteSeer (at MIT), CiteSeer (at Zurich), CiteSeer (at Singapore)

Reviews [Write a review of this article]

There are no reviews of this article

Notes for this article

bsilverthorn さんは全部で 1 非公開 + 0 公開のメモを書いています. もしあなたが bsilverthorn さんなら、ログインすれば非公開のメモを見ることができます .

Find related articles from these CiteULike users

bsilverthorn

Find related articles with these CiteULike tags

adversarial, bandit_problem, partial_information

Abstract

In the multi-armed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payoff). Past solutions for the bandit problem have almost always relied on assumptions about the...

@inproceedings{citeulike:888355, abstract = {In the multi-armed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payoff). Past solutions for the bandit problem have almost always relied on assumptions about the...}, author = {Auer, Peter and Bianchi, Nicol\`o C. and Freund, Yoav and Schapire, Robert E. }, booktitle = {Proceedings of the 36th Annual Symposium on Foundations of Computer Science}, citeulike-article-id = {888355}, keywords = {adversarial, bandit\_problem, partial\_information}, pages = {322--331}, posted-at = {2008-03-08 21:57:06}, priority = {0}, publisher = {IEEE Computer Society Press, Los Alamitos, CA}, title = {Gambling in a rigged casino: the adversarial multi-armed bandit problem}, url = {http://citeseer.ist.psu.edu/auer95gambling.html}, year = {1995} }

RIS record

TY - CONF ID - citeulike:888355 L3 - citeulike-article-id:888355 N2 - In the multi-armed bandit problem, a gambler must decide which arm of K non-identical slot machines to play in a sequence of trials so as to maximize his reward. This classical problem has received much attention because of the simple model it provides of the trade-off between exploration (trying out each arm to find the best one) and exploitation (playing the arm believed to give the best payoff). Past solutions for the bandit problem have almost always relied on assumptions about the... EP - 331 TI - Gambling in a rigged casino: the adversarial multi-armed bandit problem PB - IEEE Computer Society Press, Los Alamitos, CA T2 - Proceedings of the 36th Annual Symposium on Foundations of Computer Science SP - 322 KW - adversarial KW - bandit_problem KW - partial_information AU - Auer, Peter AU - Bianchi, Nicol\`o AU - Freund, Yoav AU - Schapire, Robert PY - 1995/// UR - http://citeseer.ist.psu.edu/auer95gambling.html ER -

RIS BibTeX