Statistical Reinforcement Learning at Harvard



We generalize existing and develop new algorithms and methods in Reinforcement Learning for use in improving health and well-being. We are particularly interesting in combining statistical methods for conducting inference (confidence intervals, hypothesis tests) with algorithmic methods developed in computer science for use in learning and evaluating treatment policies (adaptive interventions and just-in-time adaptive interventions in mobile health).

Lab Members

Software for SMART & MRT Studies can be found here

Internal Site

Susan A. Murphy,
Harvard University
Science Center 400 Suite
One Oxford Street
Cambridge, MA 02138-2901
(617) 495-5496
email: samurphy@fas.harvard.edu

[ back to top page ]