图 书 馆
一种基于效用的相对指数加权算法A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits |
|
| 课程网址: | http://videolectures.net/icml2015_gajane_dueling_bandits/ |
| 主讲教师: | Pratik Gajane |
| 开课单位: | SequeL实验室 |
| 开课时间: | 2015-09-27 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We study the K-armed dueling bandit problem which is a variation of the classical Multi-Armed Bandit (MAB) problem in which the learner receives only relative feedback about the selected pairs of arms. We propose a new algorithm called Relative Exponential-weight algorithm for Exploration and Exploitation (REX3) to handle the adversarial utility-based formulation of this problem. This algorithm is a non-trivial extension of the Exponential-weight algorithm for Exploration and Exploitation (EXP3) algorithm. We prove a finite time expected regret upper bound of order O(sqrt(K ln(K)T)) for this algorithm and a general lower bound of order omega(sqrt(KT)). At the end, we provide experimental results using real data from information retrieval applications. |
| 关 键 词: | 多武装强盗; 权重算法; 应用程序 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2022-12-07：chenjy |
| 最后编审: | 2022-12-07：chenjy |
| 阅读次数: | 28 |