Dyadic Reinforcement Learning

TL;DR

This paper introduces dyadic RL, a Bayesian hierarchical reinforcement learning algorithm designed to personalize interventions for both individuals and their care partners in mobile health, aiming to improve social support and health outcomes.

Contribution

The paper develops the first online reinforcement learning algorithm specifically targeting dyadic relationships in mobile health, with formal regret bounds and empirical validation.

Findings

Dyadic RL outperforms baseline methods in simulation studies.

The algorithm effectively personalizes interventions based on contextual and response data.

Empirical results demonstrate improved social support in simulated mobile health scenarios.

Abstract

Mobile health aims to enhance health outcomes by delivering interventions to individuals as they go about their daily life. The involvement of care partners and social support networks often proves crucial in helping individuals managing burdensome medical conditions. This presents opportunities in mobile health to design interventions that target the dyadic relationship -- the relationship between a target person and their care partner -- with the aim of enhancing social support. In this paper, we develop dyadic RL, an online reinforcement learning algorithm designed to personalize intervention delivery based on contextual factors and past responses of a target person and their care partner. Here, multiple sets of interventions impact the dyad across multiple time intervals. The developed dyadic RL is Bayesian and hierarchical. We formally introduce the problem setup, develop dyadic RL and establish a regret bound. We demonstrate dyadic RL's empirical performance through simulation studies on both toy scenarios and on a realistic test bed constructed from data collected in a mobile health study.