摘要：In the article [1], we can get a tighter upper bound of expected regret in Theorem 1 and 4, there are also some critical incorrect statements in the proof of Theorem 2, we modified the incorrect statements in this comment and a correction version of Theorem 2 is also presented.
© 2019 IEEE.

ISSN号：2160-133X

卷、期、页：v 2019-July,

发表日期：2019-07-01

期刊分区（SCI为中科院分区）：无

收录情况：EI（工程索引）

发表期刊名称：Proceedings - International Conference on Machine Learning and Cybernetics

参与作者：Li, Wei-Min,Ito, Nobuyasu

通讯作者：张鲁宁

第一作者：左信,刘建伟

论文类型：会议论文

论文概要：张鲁宁,左信,刘建伟,Li, Wei-Min,Ito, Nobuyasu，Comments on 'Finite-Time Analysis of the Multiarmed Bandit Problem'，Proceedings - International Conference on Machine Learning and Cybernetics，2019，v 2019-July,

论文题目：Comments on 'Finite-Time Analysis of the Multiarmed Bandit Problem'