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.
@article{arxiv.2201.12602,
title = {DeepRNG: Towards Deep Reinforcement Learning-Assisted Generative Testing of Software},
author = {Chuan-Yung Tsai and Graham W. Taylor},
journal= {arXiv preprint arXiv:2201.12602},
year = {2022}
}
Comments
Workshop on ML for Systems, 35th Conference on Neural Information Processing Systems (NeurIPS 2021)