IntelligentPooling: Practical Thompson Sampling for mHealth

TL;DR

IntelligentPooling is a novel reinforcement learning method that personalizes mobile health treatments by efficiently learning from limited data, adapting to non-stationary responses, and leveraging data across users to improve decision-making.

Contribution

This work introduces IntelligentPooling, a generalized Thompson Sampling algorithm that personalizes treatments, accelerates learning with cross-user data, and adapts to changing user responses in mHealth applications.

Findings

Achieves 26% lower regret than existing methods

Effective in small user groups during live clinical trials

Adapts to non-stationary user responses over time

Abstract

In mobile health (mHealth) smart devices deliver behavioral treatments repeatedly over time to a user with the goal of helping the user adopt and maintain healthy behaviors. Reinforcement learning appears ideal for learning how to optimally make these sequential treatment decisions. However, significant challenges must be overcome before reinforcement learning can be effectively deployed in a mobile healthcare setting. In this work we are concerned with the following challenges: 1) individuals who are in the same context can exhibit differential response to treatments 2) only a limited amount of data is available for learning on any one individual, and 3) non-stationary responses to treatment. To address these challenges we generalize Thompson-Sampling bandit algorithms to develop IntelligentPooling. IntelligentPooling learns personalized treatment policies thus addressing challenge one. To address the second challenge, IntelligentPooling updates each user's degree of personalization while making use of available data on other users to speed up learning. Lastly, IntelligentPooling allows responsivity to vary as a function of a user's time since beginning treatment, thus addressing challenge three. We show that IntelligentPooling achieves an average of 26% lower regret than state-of-the-art. We demonstrate the promise of this approach and its ability to learn from even a small group of users in a live clinical trial.