Optimization Method of Higher Education Resource Allocation Combined with DQN Algorithm

Abstract

At present, there are problems of low efficiency and serious waste of resources in the allocation of higher education resources. The aim of this study is to explore the potential and effectiveness of the DQN (Deep Q-Network) algorithm in higher education resource allocation, verify the advantages of the DQN algorithm in resource allocation through simulation experiments, and compare the differences in effectiveness between traditional methods and DQN methods. The study first analyzes the demand and current situation of higher education resource allocation, establishes a resource allocation model suitable for DQN algorithm, then designs the DQN algorithm framework and conducts algorithm training and testing, and finally, analyzes the performance of DQN algorithm and proposes optimization suggestions based on experimental data. The study observed that the usage rate of experimental equipment reached 90% in autumn, indicating that certain resources may face high load usage during specific time periods. This study introduces deep reinforcement learning technology into the field of higher education resource allocation, especially using DQN algorithm to optimize the decision-making process, which can achieve dynamic optimization and self adjustment of resource allocation.