Hierarchical reinforcement learning with dynamic recurrent mechanism for course recommendation

作者：

Highlights：

• We propose a HELAR model to capture user’s preferences for course recommendation.

• A policy gradient method with dynamic recurrent mechanism is proposed.

• Extensive experiments demonstrate the effectiveness of our HELAR model.

摘要

•We propose a HELAR model to capture user’s preferences for course recommendation.•A policy gradient method with dynamic recurrent mechanism is proposed.•Extensive experiments demonstrate the effectiveness of our HELAR model.

论文关键词：Recommender systems,Hierarchical reinforcement learning,Course recommendation,Policy gradient

论文评审过程：Received 24 July 2021, Revised 19 January 2022, Accepted 3 March 2022, Available online 12 March 2022, Version of Record 25 March 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108546