Research on the Optimization of Personalized Learning Paths and Teaching Practice Strategies of Deep Enhanced Learning for Dance Choreographers

Abstract The teaching of dance choreography requires that while teaching basic knowledge, the learning path should be dynamically adjusted and optimized according to the learning state of the learner to give full play to the creativity and individuality of the students, so this study proposes an optimization strategy for personalized learning path based on the deep reinforcement learning algorithm. The Actor-Critic algorithm, which combines value and strategy, is chosen as the algorithmic basis of reinforcement learning, characterizing and calculating the dynamic learning environment, respectively, and using the D3ON algorithm for personalized recommendation of dance choreography learning content. After accepting the new teaching practice strategy, the choreography students’ choreography knowledge item check-in density increased significantly and their performance showed an upward trend. The overall posttest level of dance choreography in the experimental class was significantly higher than that of the control class by 0.54 points (p<0.05), and the weak items were significantly improved. This indicates that the personalized learning path optimization strategy achieves better application value in teaching practice.