首页> 外文期刊>Foundations and trends in networking >Online Learning Methods for Networking
【24h】

Online Learning Methods for Networking

机译:联网的在线学习方法

获取原文
           

摘要

In this monograph we provide a tutorial on a family of sequential learning and decision problems known as the multi-armed bandit problems. We introduce a wide range of application scenarios for this learning framework, as well as its many different variants. The more detailed discussion is focused on the stochastic bandit problems, with rewards driven by either an IID or a Markov process, and when the environment consists of a single or multiple simultaneous users. We also present literature on the learning of MDPs, which captures coupling among the evolution of different options that a classical MAB problem does not.
机译:在这本专着中,我们提供了有关一系列顺序学习和决策问题的教程,这些问题被称为多臂匪徒问题。我们为该学习框架及其各种不同的变体引入了广泛的应用场景。更详细的讨论集中于随机的强盗问题,其奖励由IID或Markov过程驱动,以及环境由一个或多个同时用户组成。我们还提供了有关MDP学习的文献,该文献捕获了经典MAB问题所没有的不同选择之间的耦合。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号