arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09438cs.LGcs.IRstat.ML
收藏

支持不足的政策外土匪

Off-policy Bandits with Deficient Support

International Institute of Information Technology(国际信息技术研究所);Cornell University(康奈尔大学)

Noveen Sachdeva, Yi Su, Thorsten Joachims

摘要:

从已部署系统的过去动作中学习有效的上下文强盗策略在许多设置(例如语音助理、推荐、搜索)中是非常可取的,因为它能够重用大量日志数据。然而,用于这种离策略学习的现有技术方法是基于逆倾向分数(IPS)加权的。IPS加权的一个关键理论要求是记录数据的策略具有“完全支持”,这通常转化为要求任何上下文中的任何操作的非零概率。不幸的是,许多现实世界的系统产生支持不足的数据,特别是当动作空间很大,我们展示了现有的方法可以失败的灾难性。为了克服理论和应用之间的差距,我们确定了三种方法,提供各种保证基于IPS的学习,尽管支持不足的数据的固有限制:限制行动空间,奖励外推,并限制政策空间。我们系统地分析了这三种方法的统计和计算特性,并根据经验评估了它们的有效性。除了提供第一个系统的分析,支持不足的背景下,强盗学习,我们的结论与建议,提供实际的指导。

英文摘要:

Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e.g. voice assistants, recommendation, search), since it enables the reuse of large amounts of log data. State-of-the-art methods for such off-policy learning, however, are based on inverse propensity score (IPS) weighting. A key theoretical requirement of IPS weighting is that the policy that logged the data has "full support", which typically translates into requiring non-zero probability for any action in any context. Unfortunately, many real-world systems produce support deficient data, especially when the action space is large, and we show how existing methods can fail catastrophically. To overcome this gap between theory and applications, we identify three approaches that provide various guarantees for IPS-based learning despite the inherent limitations of support-deficient data: restricting the action space, reward extrapolation, and restricting the policy space. We systematically analyze the statistical and computational properties of these three approaches, and we empirically evaluate their effectiveness. In addition to providing the first systematic analysis of support-deficiency in contextual-bandit learning, we conclude with recommendations that provide practical guidance.

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。

↑