Research on Intelligent Routing Based on Reinforcement Learning
WANG Zhifeng
WU Shaofeng
Abstract：In order to improve the network performance of wireless AD hoc network and reduce the network transmission de-lay,packet loss rate and network congestion,an improved algorithm DQ-Learning is proposed based on Q-Learning algorithm.This algorithm optimizes the exploration factor ε of dynamic attenuation in Q-Learning algorithm,so that it changes slowly in the ini-tial stage,maintains a high exploration rate,and accelerates in the middle and later stages to ensure the convergence speed of the al-gorithm.The simulation results show that compared with the traditional Q-Learning algorithm and the shortest path algorithm,the improved DQ-Learning algorithm achieves better results in the indexes of delay,packet loss rate and network congestion degree,and has good application value.
Keywords：AD hoc networkreinforcement learningintelligent routingexploration factorQ-Learning
Publication Date：2025-05-20
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：4( 84-86,96 )