In this talk I discuss first solutions to some of the challenges we face in developing online RL algorithms for use in digital health interventions targeting patients struggling with health problems such as substance misuse, hypertension and bone marrow transplantation. Digital health raises a number of challenges to the statistical RL community including different sets of actions, each set intended to impact patients over a different time scale; the need to learn both within an implementation and between implementations of the RL algorithm; noisy environments and a lack of mechanistic models. In all of these settings the online line algorithm must be stable and autonomous. Despite these challenges, RL, with careful initialization, with careful management of bias/variance tradeoff and by close collaboration with health scientists can be successful. We can make an impact!
Bio of the Speaker:
Dr. Murphy's groundbreaking research focuses on improving sequential decision making in health, currently online, real-time learning algorithms for developing personalized digital health interventions. She is a member of the US National Academy of Sciences and of the US National Academy of Medicine. In 2013 she was awarded a MacArthur Fellowship for her work on experimental designs to inform sequential decision making. She has had a remarkable impact on the real-world practice of clinical trials in medical and behavior science through her research as well as efforts to promote adaptive intervention. She is a Fellow of the College on Problems in Drug Dependence.
Dr. Murphy's services to the professional community are equally outstanding. Her leadership as the former President of both IMS and Bernoulli Society, the former Editor of Annals of Statistics, and the former Chair of the Interest Group on Health and Technology of the National Academy of Medicine highlight her long-time dedication to the field. She has served on a large number of committees of professional societies and on many NIH and NSF review panels. She has trained many students and postdocs, many of whom have achieved faculty positions in leading statistics departments and received student paper awards.
About the Award:
Every year the Boston Chapter presents the Mosteller Statistician of the Year award to a distinguished statistician who has made exceptional contributions to the field of statistics and has shown outstanding service to the statistical community, including the Boston Chapter. The award was originally established in 1990 as the Statistician of the Year Award. In 1997, this award was renamed the Mosteller Statistician of the Year award in honor of the 80th birthday of its first recipient, Fred Mosteller.
