arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.10693cs.AIcs.LG
收藏

分布鲁棒策略评估与学习:基于观测数据的连续治疗

Distributionally Robust Policy Evaluation and Learning for Continuous Treatment with Observational Data

City University of Hong Kong(香港城市大学);The Hong Kong Polytechnic University(香港理工大学)

Cheuk Hang Leung, Yiyan Huang, Yijun Li, Qi Wu

AI总结:

本文针对连续治疗场景下的分布偏移问题,提出基于逆概率加权并引入核函数的分布鲁棒策略评估与学习方法,通过有限样本分析保证收敛性,实验验证其有效性。

摘要:

利用离线观测数据进行策略评估与学习,使决策者能够评估和学习一种将特征与干预措施联系起来的策略。现有文献大多关注离散治疗空间,或假设策略学习环境与策略部署环境之间的分布无差异。这些限制了许多现实场景中的应用,在这些场景中,分布偏移与连续治疗并存。为克服这些挑战,本文聚焦于在连续治疗设置下开发一种分布鲁棒策略。所提出的分布鲁棒估计量基于逆概率加权(IPW)方法建立,该方法从离散情形扩展而来,用于连续治疗下的策略评估与学习。具体而言,我们在所提出的IPW估计量中引入核函数,以减轻标准IPW方法在连续治疗中可能出现的观测排除问题。随后,我们提供了有限样本分析,保证所提出的分布鲁棒策略评估与学习估计量的收敛性。全面的实验进一步验证了我们的方法在存在分布偏移时的有效性。

英文摘要:

Using offline observational data for policy evaluation and learning allows decision-makers to evaluate and learn a policy that connects characteristics and interventions. Most existing literature has focused on either discrete treatment spaces or assumed no difference in the distributions between the policy-learning and policy-deployed environments. These restrict applications in many real-world scenarios where distribution shifts are present with continuous treatment. To overcome these challenges, this paper focuses on developing a distributionally robust policy under a continuous treatment setting. The proposed distributionally robust estimators are established using the Inverse Probability Weighting (IPW) method extended from the discrete one for policy evaluation and learning under continuous treatments. Specifically, we introduce a kernel function into the proposed IPW estimator to mitigate the exclusion of observations that can occur in the standard IPW method to continuous treatments. We then provide finite-sample analysis that guarantees the convergence of the proposed distributionally robust policy evaluation and learning estimators. The comprehensive experiments further verify the effectiveness of our approach when distribution shifts are present.

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。

↑