arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.01360cs.LG
收藏

受监督的政策外排名

Supervised Off-Policy Ranking

Tsinghua University(清华大学);University of Science and Technology of China(中国科学技术大学);Microsoft Research Asia(微软亚洲研究院)

Yue Jin, Yue Zhang, Tao Qin, Xudong Zhang, Jian Yuan, Houqiang Li, Tie-Yan Liu

摘要:

策略外评估(OPE)是利用其他策略生成的数据对目标策略进行评估。大多数以前的OPE方法专注于精确估计政策的真实表现。我们观察到,在许多应用中,(1)OPE的最终目标是比较两个或多个候选策略并选择一个好的策略,这比精确评估它们的真实性能要简单得多;(2)通常有多个策略已经部署在现实世界的系统中为用户提供服务,因此可以知道这些策略的真实性能。受这两个观察的启发,在这项工作中,我们研究了一个新的问题,监督的政策外排名(SOPR),其目的是排名一组目标政策的基础上监督学习,利用政策外的数据和政策与已知的性能。我们提出了一种解决SOPR的方法,该方法通过最小化训练策略的排名损失来学习策略评分模型,而不是估计精确的策略性能。我们的方法中的评分模型是一个基于分层Transformer的模型,它将一组状态-动作对映射到一个分数,其中每对的状态来自离线策略数据,并且目标策略以离线方式对状态采取动作。在公开数据集上的大量实验表明,该方法在秩相关性、后悔值和稳定性方面优于基线方法。我们的代码在GitHub上公开。

英文摘要:

Off-policy evaluation (OPE) is to evaluate a target policy with data generated by other policies. Most previous OPE methods focus on precisely estimating the true performance of a policy. We observe that in many applications, (1) the end goal of OPE is to compare two or multiple candidate policies and choose a good one, which is a much simpler task than precisely evaluating their true performance; and (2) there are usually multiple policies that have been deployed to serve users in real-world systems and thus the true performance of these policies can be known. Inspired by the two observations, in this work, we study a new problem, supervised off-policy ranking (SOPR), which aims to rank a set of target policies based on supervised learning by leveraging off-policy data and policies with known performance. We propose a method to solve SOPR, which learns a policy scoring model by minimizing a ranking loss of the training policies rather than estimating the precise policy performance. The scoring model in our method, a hierarchical Transformer based model, maps a set of state-action pairs to a score, where the state of each pair comes from the off-policy data and the action is taken by a target policy on the state in an offline manner. Extensive experiments on public datasets show that our method outperforms baseline methods in terms of rank correlation, regret value, and stability. Our code is publicly available at GitHub.

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。

↑