0


在部分监控的游戏中,Robust的可接近性和遗憾的最小化

Robust approachability and regret minimization in games with partial monitoring
课程网址: http://videolectures.net/colt2011_perchet_robust/  
主讲教师: Vianney Perchet
开课单位: 匹兹堡大学医学中心
开课时间: 2011-08-02
课程语种: 英语
中文简介:
在对抗性在线学习环境中,可接近性已成为分析学习算法的标准工具。我们开发了一种游戏可接近性的变体,当所获得的奖励属于一个集合而不是单个向量时,就会产生歧义。使用这种变体,我们解决了带有部分监控的游戏的可接近性问题,并开发了简单而有效的算法(即,每步复杂度不变)。最后,在部分监控的重复博弈中考虑了外部和内部的容错,并基于可达性理论推导出了最小化后悔的策略。
课程简介: Approachability has become a standard tool in analyzing learning algorithms in the adversarial online learning setup. We develop a variant of approachability for games where there is ambiguity in the obtained reward that belongs to a set, rather than being a single vector. Using this variant we tackle the problem of approachability in games with partial monitoring and develop simple and efficient algorithms (i.e., with constant per-step complexity) for this setup. We finally consider external and internal regret in repeated games with partial monitoring, for which we derive regretminimizing strategies based on approachability theory.
关 键 词: 对抗性的在线学习; 可接近性; 数学理论
课程来源: 视频讲座网
最后编审: 2020-06-08:heyf
阅读次数: 74