Online mobile learning resource recommendation method based on deep reinforcement learning

Pingyang Li and Juan Zhang

International Journal of Innovation and Sustainable Development, 2025, vol. 19, issue 1, 1-12

Abstract: In order to improve the recommendation effect of learning resources, this paper designs an online mobile learning resource recommendation method based on deep reinforcement learning. Firstly, the similarity between learners and learning resources, and the similarity between learners' search preference results and learning resources are calculated. Secondly, based on the results of similarity calculation, a multi-agent deep reinforcement learning network is designed, which includes a recommendation agent and a classification agent. Finally, according to the learners interest preferences (states) of different learning resources, the online mobile learning resources (execution actions) are recommended to the learners, and the final recommendation scheme is obtained through the recommendation agent. According to the experimental results, the maximum recommendation result hit rate of this method is 95.5%, and the highest average ranking degree is 0.926, indicating that the recommendation effect of this method is better.

Keywords: online mobile learning; learning resource; similarity; recommendation agent; classification agent; recommended scheme. (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.inderscience.com/link.php?id=142903 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ids:ijisde:v:19:y:2025:i:1:p:1-12

Access Statistics for this article

More articles in International Journal of Innovation and Sustainable Development from Inderscience Enterprises Ltd
Bibliographic data for series maintained by Sarah Parker ().