图 书 馆
multi-armed bandits的有界后悔问题Bounded regret in stochastic multi-armed bandits |
|
| 课程网址: | http://videolectures.net/colt2013_bubeck_regret/ |
| 主讲教师: | Sébastien Bubeck |
| 开课单位: | 普林斯顿大学 |
| 开课时间: | 2013-08-09 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We study the stochastic multi-armed bandit problem when one knows the value μ(⋆) of an optimal arm, as a well as a positive lower bound on the smallest positive gap Δ. We propose a new randomized policy that attains a regret uniformly bounded over time in this setting. We also prove several lower bounds, which show in particular that bounded regret is not possible if one only knows Δ, and bounded regret of order 1/Δ is not possible if one only knows μ(⋆). |
| 关 键 词: | 有界后悔; 最优化解; 随机策略 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-10-17：cwx |
| 阅读次数: | 79 |