Group-driven Reinforcement Learning for Personalized mHealth Intervention

TL;DR

This paper introduces a group-driven reinforcement learning approach for personalized mHealth interventions, leveraging user similarity clustering to improve policy learning and outperform existing methods.

Contribution

It proposes a novel clustering-based reinforcement learning framework that shares information among similar users for more effective personalized health interventions.

Findings

Achieves significant improvements over state-of-the-art RL methods.

Effectively groups users to enhance policy learning.

Demonstrates the benefit of combining clustering with reinforcement learning.

Abstract

Due to the popularity of smartphones and wearable devices nowadays, mobile health (mHealth) technologies are promising to bring positive and wide impacts on people's health. State-of-the-art decision-making methods for mHealth rely on some ideal assumptions. Those methods either assume that the users are completely homogenous or completely heterogeneous. However, in reality, a user might be similar with some, but not all, users. In this paper, we propose a novel group-driven reinforcement learning method for the mHealth. We aim to understand how to share information among similar users to better convert the limited user information into sharper learned RL policies. Specifically, we employ the K-means clustering method to group users based on their trajectory information similarity and learn a shared RL policy for each group. Extensive experiment results have shown that our method can achieve clear gains over the state-of-the-art RL methods for mHealth.