Optimization of Online Assisted Teaching Mode of College Students' Sports Based on Reinforcement Learning --Taking "LeDuoSpace APP" as an Example

Main Article Content

Xiaohu Xu, Shuai Meng


This study investigates the optimization of the online assisted teaching mode for college students' sports using reinforcement learning principles, with a focus on the "LeDuoSpace APP" platform as a case study. In response to the growing demand for innovative approaches to sports education in online environments, this research explores how reinforcement learning techniques can enhance user engagement, skill acquisition, and satisfaction within digital learning platforms. Leveraging data collected from the "LeDuoSpace APP," the study employs a rigorous experimental design to evaluate the effectiveness of the optimized teaching mode in comparison to traditional instructional methods. Statistical analysis reveals significant improvements in user engagement metrics, including a 67% increase in average session duration and a 40% rise in weekly active users. Furthermore, users exposed to the optimized teaching mode demonstrate a 25% improvement in average skill proficiency scores, highlighting the efficacy of personalized instruction and adaptive feedback mechanisms. Qualitative feedback from user satisfaction surveys further validates the positive impact of the reinforcement learning-based teaching mode on the overall learning experience. These findings contribute to the growing body of literature on the intersection of technology and education, offering insights into the potential of reinforcement learning to revolutionize sports education in online environments.

Article Details