Federated Offline Reinforcement Learning

IF 3 1区数学 Q1 STATISTICS & PROBABILITY

Journal of the American Statistical Association Pub Date : 2024-02-02 DOI:10.1080/01621459.2024.2310287

Doudou Zhou, Yufeng Zhang, Aaron Sonabend-W, Zhaoran Wang, Junwei Lu, Tianxi Cai

引用次数: 0

Abstract

Evidence-based or data-driven dynamic treatment regimes are essential for personalized medicine, which can benefit from offline reinforcement learning (RL). Although massive healthcare data are ava...

查看原文本刊更多论文

联合离线强化学习

基于证据或数据驱动的动态治疗方案对个性化医疗至关重要，而离线强化学习（RL）可以使个性化医疗受益。虽然海量的医疗保健数据已被广泛应用于临床实践，但仍有许多问题需要解决。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Journal of the American Statistical Association 数学-统计学与概率论

CiteScore

7.50

自引率

8.10%

发文量

168

审稿时长

12 months

期刊介绍： Established in 1888 and published quarterly in March, June, September, and December, the Journal of the American Statistical Association ( JASA ) has long been considered the premier journal of statistical science. Articles focus on statistical applications, theory, and methods in economic, social, physical, engineering, and health sciences. Important books contributing to statistical advancement are reviewed in JASA . JASA is indexed in Current Index to Statistics and MathSci Online and reviewed in Mathematical Reviews. JASA is abstracted by Access Company and is indexed and abstracted in the SRM Database of Social Research Methodology.