Personalized Education with Ranking Alignment Recommendation

TL;DR

This paper introduces Ranking Alignment Recommendation (RAR), a novel reinforcement learning approach for personalized question recommendation that enhances exploration efficiency by integrating collaborative ideas, leading to improved recommendation performance.

Contribution

The paper proposes RAR, a new RL-based framework that incorporates collaborative exploration strategies to improve personalized question recommendation.

Findings

RAR outperforms existing methods in recommendation accuracy

The framework is adaptable to various RL-based recommenders

Experimental results demonstrate improved exploration efficiency

Abstract

Personalized question recommendation aims to guide individual students through questions to enhance their mastery of learning targets. Most previous methods model this task as a Markov Decision Process and use reinforcement learning to solve, but they struggle with efficient exploration, failing to identify the best questions for each student during training. To address this, we propose Ranking Alignment Recommendation (RAR), which incorporates collaborative ideas into the exploration mechanism, enabling more efficient exploration within limited training episodes. Experiments show that RAR effectively improves recommendation performance, and our framework can be applied to any RL-based question recommender. Our code is available in https://github.com/wuming29/RAR.git.