基于深度Q-学习和粒子群优化的僵尸检测算法

Deep Q-Learning and Particle Swarm Optimization-based Bot Detection Algorithm

深度Q-学习算法常用于检测社会网络平台上的僵尸攻击。但是Q-学习算法的收敛慢。为此,提出基于深度Q-学习和粒子群优化的僵尸检测(Deep Q-Learning and Particle Swarm Optimization-based Bot Detection,DQL-PSO)算法。DQL-PSO算法引用粒子群优化算法提高Q-学习算法性能,进而获取最优的学习动作序列。将学习动作序列作为粒子的位置;将状态转换概率转换成粒子速度,进而利用粒子群优化算法提升Q-学习算法性能。仿真结果表明,提出的DQL-PSO算法提高了僵尸检测的准确率,并提升了收敛速度。

Deep Q-learning algorithm is used to detect bots.However,in traditional Q-learning algorithm,convergence of Q-learning will be slow.Therefore,deep Q-learning and particle swarm optimization-based bot detection(DQL-PSO)algorithm is proposed in this paper.A particle swarm optimization method is adopted to improve Q-learning in order to obtain an optimal sequence of learning actions.This paper defines position of particle as a sequence of learning actions and the velocity of particle as state transition probability values.The experiment results illustrate the DQL-PSO algorithm outperform traditional Q-learning algorithm in terms of precision and convergence.