STRL:基于强化学习的测试算法  

STRL:Testing Algorithm Based on Reinforcement Learning

作　　者：赵花蕊 ZHAO Huarui(Platform Economy Development Guidance Center of Henan Province,Zhengzhou 450008,China)

机构地区：[1]河南省平台经济发展指导中心,河南郑州450008

出　　处：《计算机与现代化》2024年第8期5-10,共6页Computer and Modernization

摘　　要：强化学习因为不需要大量样本进行训练而采用与环境交互的方式产生动态数据的特点,使得强化学习成为近些年机器学习领域的研究热点。本文提出一种新的基于强化学习的软件测试框架STRL,能有效解决回归测试耗时时间久,状态覆盖率低的问题。STRL利用强化学习算法PPO实现高效的自适应探索。实验结果表明,STRL算法在状态覆盖率和测试时间方面都优于人工测试和自动化脚本测试。Reinforcement learning has become research focus in the field of machine learning in recent years due to its character⁃istic of generating dynamic data through interaction with the environment without requiring a large number of samples for training.This paper proposes a new software testing framework STRL based on reinforcement learning,which can effectively solve the problem of long time consuming and low state coverage of regression testing.STRL utilizes reinforcement learning algorithm PPO to achieve efficient adaptive exploration.Experiments results show that the STRL algorithm outperforms manual testing and auto⁃mated script testing in terms of state coverage and testing time.

关 键 词：人工智能软件 智能化软件 传统软件 软件生命周期 强化学习 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]