English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Personalization is very powerful in improving the effectiveness of healthinterventions. Reinforcement learning (RL) algorithms are suitable for learningthese tailored interventions from sequential data collected about individuals.However, learning can be very fragile. The time to learn intervention policiesis limited as disengagement from the user can occur quickly. Also, in e-Healthintervention timing can be crucial before the optimal window passes. We presentan approach that learns tailored personalization policies for groups of usersby combining RL and clustering. The benefits are two-fold: speeding up thelearning to prevent disengagement while maintaining a high level ofpersonalization. Our clustering approach utilizes dynamic time warping tocompare user trajectories consisting of states and rewards. We apply online andbatch RL to learn policies over clusters of individuals and introduce ourself-developed and publicly available simulator for e-Health interventions toevaluate our approach. We compare our methods with an e-Health interventionbenchmark. We demonstrate that batch learning outperforms online learning forour setting. Furthermore, our proposed clustering approach for RL findsnear-optimal clusterings which lead to significantly better policies in termsof cumulative reward compared to learning a policy per individual or learningone non-personalized policy across all individuals. Our findings also indicatethat the learned policies accurately learn to send interventions at the rightmoments and that the users workout more and at the right times of the day.

A clustering-based reinforcement learning approach for tailored personalization of e-Health interventions