Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 3 - Individualized Treatment Rules
Type: Invited
Date/Time: Monday, August 3, 2020 : 10:00 AM to 11:50 AM
Sponsor: Biometrics Section
Abstract #308067
Title: Online Reinforcement Learning with Applications to Mobile Health
Author(s): Susan Murphy and Peng Liao* and Sabina Tomkins and Predrag Klasnja
Companies: Harvard University and Harvard University and Stanford University and University of Michigan
Keywords: machine learning; reinforcement learning; mobile health

In this talk we describe two reinforcement learning algorithms we have implemented in a mobile health physical activity trial. These algorithms are designed to tackle two challenges faced by mobile health. The first challenge is that while most treatments delivered by a mobile device have immediate nonnegative (hopefully positive) effects, longer term effects tend to be negative due to user burden. To address this first challenge we add a low variance proxy for the delay effects to the reward (e.g. immediate response) in the learning algorithm. The second challenge is that data on any one individual is very noisy making it difficult for the algorithm to learn. To address this challenge we pool data across participants via a Bayesian multilevel learning algorithm.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program