Group-driven Reinforcement Learning for Personalized mHealth Intervention
This work addresses the challenge of effective decision-making for personalized mHealth interventions, which is incremental as it builds on existing RL methods by introducing a clustering-based grouping strategy.
The paper tackles the problem of personalizing mobile health interventions by addressing the limitations of existing methods that assume users are either completely homogeneous or heterogeneous, proposing a group-driven reinforcement learning approach that clusters users based on trajectory similarity to learn shared policies, which achieves clear gains over state-of-the-art RL methods in experiments.
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.