arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.01047econ.EMcs.LG
收藏

动态最优处理分配

Dynamically Optimal Treatment Allocation

University of Pennsylvania(宾夕法尼亚大学);University of Bern(伯尔尼大学)

Karun Adusumilli, Friedrich Geiecke, Claudio Schilter

AI总结:

本文研究在预算和容量约束下如何利用随机对照试验证据进行动态个性化决策,证明受限策略类的遗憾以 n^(-0.5) 速率衰减,并在职业培训应用中验证其优于静态方法。

摘要:

动态决策对经济政策制定至关重要。我们展示了如何利用来自随机对照试验的现有证据,在具有预算和容量约束的挑战性动态环境中指导个性化决策。强化学习的最新进展首次使得许多复杂的现实世界问题的求解成为可能。我们允许受限的策略函数类,并证明其遗憾以 n^(-0.5) 的速率衰减,与静态情形相同。将我们的方法应用于职业培训,我们发现通过利用问题的动态结构,与静态方法相比,我们实现了显著更高的福利。

英文摘要:

Dynamic decisions are pivotal to economic policy making. We show how existing evidence from randomized control trials can be utilized to guide personalized decisions in challenging dynamic environments with budget and capacity constraints. Recent advances in reinforcement learning now enable the solution of many complex, real-world problems for the first time. We allow for restricted classes of policy functions and prove that their regret decays at rate n^(-0.5), the same as in the static case. Applying our methods to job training, we find that by exploiting the problem's dynamic structure, we achieve significantly higher welfare compared to static approaches.

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。

↑