论文标题
Deeprng：朝着深入增强软件学习的生成测试
DeepRNG: Towards Deep Reinforcement Learning-Assisted Generative Testing of Software
论文作者
论文摘要
尽管机器学习（ML）在自动化各种软件工程需求方面已经成功，但软件测试仍然是一个高度挑战的主题。在本文中，我们旨在通过使用有效的，可自动提取的软件对正在测试的软件的自动提取的状态表示，通过直接增强随机数生成器（RNG）来改善软件的生成测试。使用Cosmos SDK作为测试床，我们表明，提出的DeepRng框架为具有超过350,000行代码的高度复杂软件库的测试提供了统计学上的显着改进。 Deeprng框架的源代码在线公开可用。
Although machine learning (ML) has been successful in automating various software engineering needs, software testing still remains a highly challenging topic. In this paper, we aim to improve the generative testing of software by directly augmenting the random number generator (RNG) with a deep reinforcement learning (RL) agent using an efficient, automatically extractable state representation of the software under test. Using the Cosmos SDK as the testbed, we show that the proposed DeepRNG framework provides a statistically significant improvement to the testing of the highly complex software library with over 350,000 lines of code. The source code of the DeepRNG framework is publicly available online.
