arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1503.06169cs.LG
收藏

具有组合策略的网络化随机多臂强盗

Networked Stochastic Multi-Armed Bandits with Combinatorial Strategies

University of Texas at Dallas(德克萨斯大学达拉斯分校);Singapore University of Technology and Design(新加坡科技设计大学)

Shaojie Tang, Yaqin Zhou

摘要:

在本文中,我们研究了一个很大程度上扩展版本的经典MAB问题,称为网络组合强盗问题。特别地,我们考虑了决策者在网络化强盗上的设置如下:每次组合策略,例如,选择一组手臂,决策者收到她的策略产生的奖励,也收到每个手臂邻居的策略产生的附加奖励。这是由许多真实的应用程序,如在线社交网络,其中朋友可以提供他们的反馈共享内容,因此,如果我们向用户推广产品,我们也可以收集反馈,她的朋友对该产品。为此,我们在这项研究中考虑了两种类型的边奖金:边观察和边奖励。根据每个时间段的手臂拉动次数,我们研究了两种情况:单人游戏和组合游戏。因此,这给我们留下了四个场景来研究存在边奖金的情况:带边观察的单人游戏,带边观察的组合游戏,带边奖励的单人游戏和带边奖励的组合游戏。对于每一种情况下,我们提出并分析了一系列的\emph{zero regret}政策,随着时间的推移,随着时间的推移,后悔的期望接近零。大量的模拟验证了我们的结果的有效性。

英文摘要:

In this paper, we investigate a largely extended version of classical MAB problem, called networked combinatorial bandit problems. In particular, we consider the setting of a decision maker over a networked bandits as follows: each time a combinatorial strategy, e.g., a group of arms, is chosen, and the decision maker receives a reward resulting from her strategy and also receives a side bonus resulting from that strategy for each arm's neighbor. This is motivated by many real applications such as on-line social networks where friends can provide their feedback on shared content, therefore if we promote a product to a user, we can also collect feedback from her friends on that product. To this end, we consider two types of side bonus in this study: side observation and side reward. Upon the number of arms pulled at each time slot, we study two cases: single-play and combinatorial-play. Consequently, this leaves us four scenarios to investigate in the presence of side bonus: Single-play with Side Observation, Combinatorial-play with Side Observation, Single-play with Side Reward, and Combinatorial-play with Side Reward. For each case, we present and analyze a series of \emph{zero regret} polices where the expect of regret over time approaches zero as time goes to infinity. Extensive simulations validate the effectiveness of our results.

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。

↑