Group-driven Reinforcement Learning for Personalized mHealth Intervention

By Feiyun Zhu, Jun Guo, Zheng Xu, Peng Liao, Junzhou Huang. 2017

20 citations recorded by the source corpus.

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.

Subfields: Applied Psychology, Computer Vision and Pattern Recognition, General Health Professions

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In General Health Professions

Citations in the corpus

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “tability is given as the deviation of the features of unhealthy subject from the age norm. On a different note, reinforcement learning (RL) has been applied to personalized healthcare. In particular, [133] introduces group-driven RL in personalized healthcare, taking into considerations different gr”
Reinforcement Learning in Healthcare: A Survey (2019, methodology): “For example, RL has been used to adapt the intervention strategies of smart phones to recommend regular physical activities to people who suffer from diabetes type 2 [84, 246] or who have experienced a cardiac event and been in cardiac rehab [119, 256, 257].”
Robust Actor-Critic Contextual Bandit for Mobile Health (mHealth) Interventions (2018, methodology): “There are nine contextual bandit methods compared in the experiment, including three state-of-the-art methods: (1) Linear Upper Confidence Bound Algorithm (LinUCB) is one of the most famous contextual bandit methods used in the personalized news recommendation [12, 18]; (2) the actor-critic contextu”
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches (2018, methodology): “In this work, K-means clustering is applied for grouping the people and finally shared with RL policy for each group [245].”