图 书 馆
在随机环境下部分监控游戏的极小极大遗憾Minimax Regret of Finite Partial-Monitoring Games in Stochastic Environments |
|
| 课程网址: | http://videolectures.net/colt2011_bartok_games/ |
| 主讲教师: | Gábor Bartók |
| 开课单位: | 苏黎世联邦理工学院 |
| 开课时间: | 2011-08-02 |
| 课程语种: | 英语 |
| 中文简介: |  |
| 课程简介: | In a partial monitoring game, the learner repeatedly chooses an action, the environment responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which are fixed functions of the action and the outcome. The goal of the learner is to minimize his regret, which is the difference between his total cumulative loss and the total loss of the best fixed action in hindsight. Assuming that the outcomes are generated in an i.i.d. fashion from an arbitrary and unknown probability distribution, we characterize the minimax regret of any partial monitoring game with finitely many actions and outcomes. It turns out that the minimax regret of any such game is either zero,Ɵ(√T), Ɵ(T2/3) or Ɵ(T). We provide a computationally efficient learning algorithm that achieves the minimax regret within logarithmic factor for any game. |
| 关 键 词: | 概率; 部分监控游戏; 学习算法 |
| 课程来源: | 视频讲座网 |
| 最后编审: | 2020-07-16：yumf |
| 阅读次数: | 64 |