Application of Reinforcement Learning in Personalized Learning Path Recommendation in Secondary Education Management

With the increasing demand for improving the quality of secondary education, accurately recommending personalized learning faces the challenge of data redundancy. Traditional educational management methods are insufficient to meet the different learning needs of students, which makes it difficult to obtain effective and personalized matching, thereby affecting learning efficiency. This paper conducts in-depth research on personalized learning paths by simulating the learning behavior optimized by reinforcement learning algorithms. The system can respond in real-time to changes in students’ learning status and needs, and propose learning paths that are suitable for their characteristics and interests. This paper tests a personalized learning path model, and the experimental results shows that the highest accuracy of the personalized learning path recommended by reinforcement learning is $98 \%$. This indicates a significant improvement in the accuracy of personalized knowledge push models, which can provide students with learning path models that are more suitable for their needs.