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 2008.06668cs.LGstat.ML
收藏

基于核Bellman统计量的负责任离策略评估

Accountable Off-Policy Evaluation With Kernel Bellman Statistics

The University of Texas at Austin(德克萨斯大学奥斯汀分校)

Yihao Feng, Tongzheng Ren, Ziyang Tang, Qiang Liu

摘要:

我们考虑了政策外评估(OPE),它根据从以前的实验中收集的观察数据来评估新政策的性能,而不需要执行新政策。这在具有高执行成本或安全问题的领域中找到了重要的应用,例如医疗诊断,推荐系统和机器人技术。在实际应用中,由于非策略数据所提供的信息有限,因此需要构造严格的置信区间,而不仅仅是点估计。在这项工作中,我们提出了一个新的变分框架,减少了问题的计算紧的置信界限OPE到一个可行的集合上的优化问题,捕获真正的状态动作价值函数具有高概率。通过利用最近提出的内核Bellman损失的统计特性来构造可行集(Feng等人,2019年)。我们设计了一个有效的计算方法来计算我们的界限,并将其扩展到执行事后诊断和校正现有的估计。实证结果表明,我们的方法在不同的设置产生紧的置信区间。

英文摘要:

We consider off-policy evaluation (OPE), which evaluates the performance of a new policy from observed data collected from previous experiments, without requiring the execution of the new policy. This finds important applications in areas with high execution cost or safety concerns, such as medical diagnosis, recommendation systems and robotics. In practice, due to the limited information from off-policy data, it is highly desirable to construct rigorous confidence intervals, not just point estimation, for the policy performance. In this work, we propose a new variational framework which reduces the problem of calculating tight confidence bounds in OPE into an optimization problem on a feasible set that catches the true state-action value function with high probability. The feasible set is constructed by leveraging statistical properties of a recently proposed kernel Bellman loss (Feng et al., 2019). We design an efficient computational approach for calculating our bounds, and extend it to perform post-hoc diagnosis and correction for existing estimators. Empirical results show that our method yields tight confidence intervals in different settings.

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。

↑