Research on an Algorithm for Optimizing the Training Effect of Basketball Players Using Big Data

This paper proposes an innovative training effect optimization algorithm based on DRL. The algorithm combines the multi-dimensional data of basketball players (such as running trajectory, shooting accuracy, physical data, etc.) and formulates and adjusts personalized training strategies through the DQN model. Specifically, the agent selects different training intensities, contents and methods according to the current training status and performance of the athletes, and dynamically optimizes the strategy according to the feedback of the training effect. The experimental results show that compared with the traditional training method, the training optimization algorithm based on DRL can significantly improve the training effect. Specifically, the improvement of athletes in skill improvement is more than <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 0 \%}$</tex>, and the physical recovery is also effectively optimized. At the same time, the algorithm can adapt to the changing needs of each athlete in real time and provide customized training plans. The experiment also shows that the training effect of the algorithm on large-scale sports data sets is stable, and it has strong versatility and flexibility.