BriefGPT.xyz
May, 2018
清理社区:对抗性部分监督的完整分类
Cleaning up the neighborhood: A full classification for adversarial partial monitoring
HTML
PDF
Tor Lattimore, Csaba Szepesvari
TL;DR
本文研究了有限敌对情况下的部分监督,在解决Bartok等人提出的开放性问题的基础上,研究了在Bartok [2013]的研究中的游戏类别的新算法,对遗憾与游戏结构的相关性进行了探讨,并简化改进了现有算法并纠正了以前的分析错误。
Abstract
partial monitoring
is a generalization of the well-known
multi-armed bandit
framework where the loss is not directly observed by the learner. We complete the classification of finite
→