图 书 馆
一种简单的多臂强盗算法，具有最佳变异 - 有界遗憾A simple multi-armed bandit algorithm with optimal variation-bounded regret |
|
| 课程网址: | http://videolectures.net/colt2011_hazan_regret/ |
| 主讲教师: | Elad Hazan |
| 开课单位: | 以色列理工学院 |
| 开课时间: | 2011-08-02 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We pose the question of whether it is possible to design a simple, linear-time algorithm for the basic multi-armed bandit problem in the adversarial setting which has a regret bound of O(√QlogT), where Q is the total quadratic variation of all the arms. |
| 关 键 词: | 线性; 算法; 多武装强盗问题 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-03-06：lxf |
| 阅读次数: | 148 |