A note on strategies for bandit problems with infinitely many arms

淡江大學機構典藏 > 理學院 > 數學學系暨研究所 > 期刊論文 > Item 987654321/41423

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/41423

题名:	A note on strategies for bandit problems with infinitely many arms
作者:	陳功宇;Chen, Kung-yu;林千代;Lin, Chien-tai
贡献者:	淡江大學數學學系
关键词:	K-failure strategy;M-run strategy;Nn-learning strategy;Non-recalling m-run strategy k-failure strategy;m-run strategy;Nn-learning strategy;non-recalling m-run strategy
日期:	2004-05
上传时间:	2010-01-28 07:32:01 (UTC+8)
出版者:	Springer
摘要:	A bandit problem consisting of a sequence of n choices (n→∞) from a number of infinitely many Bernoulli arms is considered. The parameters of Bernoulli arms are independent and identically distributed random variables from a common distribution F on the interval [0,1] and F is continuous with F(0)=0 and F(1)=1. The goal is to investigate the asymptotic expected failure rates of k-failure strategies, and obtain a lower bound for the expected failure proportion over all strategies presented in Berry et al. (1997). We show that the asymptotic expected failure rates of k-failure strategies when 0<b≤1 and a lower bound can be evaluated if the limit of the ratio F(1)−F(t) versus (1−t)b exists as t→1− for some b>0.
關聯:	Metrika 59(2), pp.193-203
DOI:	10.1007/s001840300279
显示于类别:	[數學學系暨研究所] 期刊論文

文件中的档案:

档案	大小	格式	浏览次数
A note on strategies for bandit problems with infinitely many arms.pdf	253Kb	Adobe PDF	1	检视/开启
index.html	0Kb	HTML	194	检视/开启
index.html	0Kb	HTML	132	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章