Learning When-to-Treat Policies

• 成果类型: Article
• 署名作者: Nie, Xinkun; Brunskill, Emma; Wager, Stefan
• 署名单位: Stanford University; Stanford University
• 刊物名称: JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
• ISSN/ISSBN: 0162-1459
• DOI: 10.1080/01621459.2020.1831925
• 发表日期: 2020
• 页码: 392-409
• 关键词: MARGINAL STRUCTURAL MODELS; Dynamic Treatment Regimes; Causal Inference; treatment rules; nested models

摘要

Many applied decision-making problems have a dynamic component: The policymaker needs not only to choose whom to treat, but also when to start which treatment. For example, a medical doctor may choose between postponing treatment (watchful waiting) and prescribing one of several available treatments during the many visits from a patient. We develop an advantage doubly robust estimator for learning such dynamic treatment rules using observational data under the assumption of sequential ignorability. We prove welfare regret bounds that generalize results for doubly robust learning in the single-step setting, and show promising empirical performance in several different contexts. Our approach is practical for policy optimization, and does not need any structural (e.g., Markovian) assumptions. for this article are available online.