arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1506.04782cs.LGstat.ML
收藏

廉价老虎机

Cheap Bandits

Boston University(波士顿大学);INRIA Lille - Nord Europe(法国国家信息与自动化研究所里尔-北欧研究中心);Google DeepMind(谷歌DeepMind)

Manjesh Kumar Hanawal, Venkatesh Saligrama, Michal Valko, R\' emi Munos

AI总结:

本文针对可观察多动作平均奖励的随机序贯学习问题,提出CheapUCB算法,在平滑图假设下同时最小化感知成本并匹配遗憾保证,并推导出谱老虎机的Ω(√(dT))下界。

摘要:

我们考虑随机序贯学习问题,其中学习者可以观察多个动作的平均奖励。这种设置在涉及监测和监视的许多应用中很有趣,在这些应用中,要观察的动作集合代表某个(地理)区域。该设置的重要性在于,在这些应用中,观察一组动作的平均奖励实际上比观察单个动作的奖励更便宜。我们证明,当奖励在表示相邻动作的给定图上平滑时,我们可以在最小化感知成本的同时最大化学习的累积奖励。在本文中,我们提出了CheapUCB算法,该算法在该设置下匹配已知算法的遗憾保证,同时相对于它们保证线性成本。作为我们分析的副产品,我们为有效维度为d的一类图建立了谱老虎机累积遗憾的Ω(√(dT))下界。

英文摘要:

We consider stochastic sequential learning problems where the learner can observe the \textit{average reward of several actions}. Such a setting is interesting in many applications involving monitoring and surveillance, where the set of the actions to observe represent some (geographical) area. The importance of this setting is that in these applications, it is actually \textit{cheaper} to observe average reward of a group of actions rather than the reward of a single action. We show that when the reward is \textit{smooth} over a given graph representing the neighboring actions, we can maximize the cumulative reward of learning while \textit{minimizing the sensing cost}. In this paper we propose CheapUCB, an algorithm that matches the regret guarantees of the known algorithms for this setting and at the same time guarantees a linear cost again over them. As a by-product of our analysis, we establish a $Ω(\sqrt{dT})$ lower bound on the cumulative regret of spectral bandits for a class of graphs with effective dimension $d$.

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。

↑