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 2209.08682cs.LGstat.ML
收藏

通过人为输入实现稳健的政策外评估

Towards Robust Off-Policy Evaluation via Human Inputs

New York University(纽约大学);Harvard University(哈佛大学)

Harvineet Singh, Shalmali Joshi, Finale Doshi-Velez, Himabindu Lakkaraju

摘要:

政策外评估(OPE)方法是评估高风险领域(如医疗保健)政策的重要工具,在这些领域,直接部署通常是不可行的,不道德的或昂贵的。当部署环境预计会发生变化(即数据集变化)时,OPE方法必须在这些变化中对策略进行健壮的评估。现有的方法考虑对一个大类的变化,可以任意改变任何可观察到的环境属性的鲁棒性。这通常会导致对实用程序的高度悲观的估计,从而使可能在部署中有用的策略无效。在这项工作中,我们解决了上述问题,通过调查领域知识如何可以帮助提供更现实的估计政策的效用。我们利用人类输入的环境方面可能会发生变化,并调整OPE方法,只考虑这些方面的变化。具体来说,我们提出了一个新的框架,鲁棒OPE(ROPE),它考虑了基于用户输入的数据中的协变量子集的变化,并估计这些变化下的最坏情况下的效用。然后,我们开发计算效率高的算法OPE是强大的上下文土匪和马尔可夫决策过程的上述变化。我们还从理论上分析了这些算法的样本复杂度。对来自医疗保健领域的合成和真实世界数据集的广泛实验表明,我们的方法不仅准确地捕捉了现实的数据集变化,而且还导致了不那么悲观的政策评估。

英文摘要:

Off-policy Evaluation (OPE) methods are crucial tools for evaluating policies in high-stakes domains such as healthcare, where direct deployment is often infeasible, unethical, or expensive. When deployment environments are expected to undergo changes (that is, dataset shifts), it is important for OPE methods to perform robust evaluation of the policies amidst such changes. Existing approaches consider robustness against a large class of shifts that can arbitrarily change any observable property of the environment. This often results in highly pessimistic estimates of the utilities, thereby invalidating policies that might have been useful in deployment. In this work, we address the aforementioned problem by investigating how domain knowledge can help provide more realistic estimates of the utilities of policies. We leverage human inputs on which aspects of the environments may plausibly change, and adapt the OPE methods to only consider shifts on these aspects. Specifically, we propose a novel framework, Robust OPE (ROPE), which considers shifts on a subset of covariates in the data based on user inputs, and estimates worst-case utility under these shifts. We then develop computationally efficient algorithms for OPE that are robust to the aforementioned shifts for contextual bandits and Markov decision processes. We also theoretically analyze the sample complexity of these algorithms. Extensive experimentation with synthetic and real world datasets from the healthcare domain demonstrates that our approach not only captures realistic dataset shifts accurately, but also results in less pessimistic policy evaluations.

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。

↑