Personalization of Health Interventions Using Cluster-Based Reinforcement Learning

Ali Hassouni, Mark Hoogendoorn, Martijn van Otterlo, E. Barbaro

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

11 Citations (Scopus)

Abstract

Research has shown that personalization of health interventions can contribute to an improved effectiveness. Reinforcement learning algorithms can be used to perform such tailoring. In this paper, we present a cluster-based reinforcement learning approach which learns optimal policies for groups of users. Such an approach can speed up the learning process while still giving a level of personalization. We apply both online and batch learning to learn policies over the clusters and introduce a publicly available simulator which we have developed to evaluate the approach. The results show batch learning significantly outperforms online learning. Furthermore, near-optimal clustering is found which proves to be beneficial in learning significantly better policies compared to learning per user and learning across all users.
Original languageEnglish
Title of host publicationPRIMA 2018: Principles and Practice of Multi-Agent Systems
Subtitle of host publicationLecture Notes in Computer Science
Volume11224
DOIs
Publication statusPublished - 2018
EventInternational Conference on Principles and Practice of Multi-Agent Systems - Tokyo, Japan
Duration: 29 Oct 20182 Nov 2018
Conference number: 21
http://2018.prima-conference.org/

Conference

ConferenceInternational Conference on Principles and Practice of Multi-Agent Systems
Abbreviated titlePRIMA 2018
Country/TerritoryJapan
CityTokyo
Period29/10/182/11/18
Internet address

Fingerprint

Dive into the research topics of 'Personalization of Health Interventions Using Cluster-Based Reinforcement Learning'. Together they form a unique fingerprint.

Cite this