Mistake bounds on the noise-free multi-armed bandit game

Atsuyoshi Nakamura,David P. Helmbold,Manfred K. Warmuth

Information and Computation（2019）

引用 1|浏览39

暂无评分

摘要

We study the {0,1}-loss version of adaptive adversarial multi-armed bandit problems with α(≥1) lossless arms. For the problem, we show a tight bound K−α−Θ(1/T) on the minimax expected number of mistakes (1-losses), where K is the number of arms and T is the number of rounds.

查看译文

关键词

Computational learning theory,Online learning,Bandit problem,Mistake bound

AI 理解论文

溯源树

样例

生成溯源树，研究论文发展脉络

Chat Paper

正在生成论文摘要