期刊
MACHINE LEARNING
卷 84, 期 1-2, 页码 109-136出版社
SPRINGER
DOI: 10.1007/s10994-010-5229-0
关键词
Optimal treatment policies; Fitted Q-iteration; Policy uncertainty
资金
- National Institutes of Health (NIH) [R01 MH080015, P50 DA10075]
- Natural Sciences and Engineering Research Council of Canada (NSERC)
- Canadian Institutes of Health Research (CIHR)
This paper highlights the role that reinforcement learning can play in the optimization of treatment policies for chronic illnesses. Before applying any off-the-shelf reinforcement learning methods in this setting, we must first tackle a number of challenges. We outline some of these challenges and present methods for overcoming them. First, we describe a multiple imputation approach to overcome the problem of missing data. Second, we discuss the use of function approximation in the context of a highly variable observation set. Finally, we discuss approaches to summarizing the evidence in the data for recommending a particular action and quantifying the uncertainty around the Q-function of the recommended policy. We present the results of applying these methods to real clinical trial data of patients with schizophrenia.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据