arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.04339cs.LG
收藏

部分揭示单位区间图上的多臂强盗

Multi-Armed Bandits on Partially Revealed Unit Interval Graphs

Cornell University(康奈尔大学);CCDC Army Research Laboratory(CCDC陆军研究实验室);Chalmers University(查尔姆斯大学)

Xiao Xu, Sattar Vakili, Qing Zhao, Ananthram Swami

摘要:

研究了一类随机多臂强盗问题,该问题具有不同臂之间相似性和相异性的边信息。问题的动作空间可以用单位区间图(UIG)表示,其中每个节点表示一个手臂,两个节点之间的边的存在(不存在)表明它们的平均奖励之间的相似性(不相似性)。两个设置的完整和部分侧信息的基础上是否UIG是完全揭示的研究和一般的两步学习结构,包括离线减少的动作空间和在线聚合的奖励观察从类似的武器,提出了充分利用的拓扑结构的侧信息。在这两种情况下,所提出的学习策略的计算效率和顺序最优性的动作空间的大小和时间长度的。

英文摘要:

A stochastic multi-armed bandit problem with side information on the similarity and dissimilarity across different arms is considered. The action space of the problem can be represented by a unit interval graph (UIG) where each node represents an arm and the presence (absence) of an edge between two nodes indicates similarity (dissimilarity) between their mean rewards. Two settings of complete and partial side information based on whether the UIG is fully revealed are studied and a general two-step learning structure consisting of an offline reduction of the action space and online aggregation of reward observations from similar arms is proposed to fully exploit the topological structure of the side information. In both cases, the computation efficiency and the order optimality of the proposed learning policies in terms of both the size of the action space and the time length are established.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑