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).
Software for SMART & MRT Studies can be found here and here.
Susan A. Murphy,[ back to top page ]