图 书 馆
具有侧面观测的分段 - 平稳强盗问题Piecewise-Stationary Bandit Problems with Side Observations |
|
| 课程网址: | http://videolectures.net/icml09_yu_psbp/ |
| 主讲教师: | Jia Yuan Yu |
| 开课单位: | 麦吉尔大学 |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | We consider a sequential decision problem where the rewards are generated by a piecewise-stationary distribution. However, the different reward distributions are unknown and may change at unknown instants. Our approach uses a limited number of side observations on past rewards, but does not require prior knowledge of the frequency of changes. In spite of the adversarial nature of the reward process, we provide an algorithm whose regret, with respect to the baseline with perfect knowledge of the distributions and the changes, is O(k \log(T), where k is the number of changes up to time T. This is in contrast to the case where side observations are not available, and where the regret is at least Omega(sqrt{T}). |
| 关 键 词: | 顺序决策; 分段静止; 奖励分布 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2019-04-25：cwx |
| 阅读次数: | 31 |