We used RL; but did it work? | Susan Murphy, Harvard University


Friday, November 12, 2021, 1:00pm to 2:00pm



Susan Murphy Picture
Susan Murphy
Professor of Statistics, 
Radcliffe Alumnae Professor, Radcliffe Institute, Harvard University
Professor of Computer Science,  
Harvard John A. Paulson School of Engineering and Applied Sciences

Registration is required for this event. Click here to register.

ABSTRACT: Reinforcement Learning provides an attractive suite of online learning methods for personalizing interventions in a Digital Health. However after an reinforcement learning algorithm has been run in a clinical study, how do we assess whether personalization occurred? We might find users for whom it appears that the algorithm has indeed learned in which contexts the user is more responsive to a particular intervention. But could this have happened completely by chance? We discuss some first approaches to addressing these questions.

BIO: Murphy’s research focuses on improving sequential, individualized, decision making in health, in particular, clinical trial design and data analysis to inform the development of just-in-time adaptive interventions in digital health. She developed the micro-randomized trial for use in constructing digital health interventions; this trial design is in use across a broad range of health-related areas. Her lab works on online learning algorithms for developing personalized digital health interventions. She is a 2013 MacArthur Fellow, a member of the National Academy of Sciences and the National Academy of Medicine, both of the US National Academies.