arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.13078stat.MLcs.LGmath.STstat.TH
收藏

更新还是不更新?随机分配的时滞非参数Bands

To update or not to update? Delayed Nonparametric Bandits with Randomized Allocation

University of Minnesota(明尼苏达大学)

Sakshi Arya, Yuhong Yang

摘要:

背景强盗中的延迟报酬问题在各种实际环境中都引起了人们的兴趣。我们研究了随机分配策略,并提供了一个了解如何探索剥削权衡的延迟观察奖励的影响。在随机策略中,探索-开发的程度由用户确定的探索概率序列控制。在存在延迟奖励的情况下,人们可以选择使用在每个时间点更新的原始探索序列,或者仅在观察到新奖励时更新序列,从而导致两种竞争策略。在这项工作中,我们表明,虽然这两种策略可能会导致很强的一致性分配,后者的财产持有更广泛的情况。然而,对于有限样本的性能,我们说明了这两种策略都有自己的优点和缺点,这取决于延迟的严重程度和潜在的奖励产生机制。

英文摘要:

Delayed rewards problem in contextual bandits has been of interest in various practical settings. We study randomized allocation strategies and provide an understanding on how the exploration-exploitation tradeoff is affected by delays in observing the rewards. In randomized strategies, the extent of exploration-exploitation is controlled by a user-determined exploration probability sequence. In the presence of delayed rewards, one may choose between using the original exploration sequence that updates at every time point or update the sequence only when a new reward is observed, leading to two competing strategies. In this work, we show that while both strategies may lead to strong consistency in allocation, the property holds for a wider scope of situations for the latter. However, for finite sample performance, we illustrate that both strategies have their own advantages and disadvantages, depending on the severity of the delay and underlying reward generating mechanisms.

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。

↑