Fault Diversity in Reinforcement Learning Policy Testing
ACM Transactions on Software Engineering and Methodology · 29.06.2026
DOI: 10.1145/3821533 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 29.06.2026. Verfasst von Quentin Mazouni und 3 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben.
Abstract (Originalsprache)
Reinforcement Learning (RL) is the common approach to solving sequential decision-making problems. Testing is an effective method for detecting functional faults in RL policies. Not only should policy testing find as many failures as possible, but it should also reveal diverse ones. In that regard, Quality diversity optimization (QD) is a type of evolutionary algorithm that returns a set of high-quality diverse solutions. In this article, we explore the use of Quality Diversity to tackle fault diversity in policy testing. We define and address the challenges of adapting QD to testing policies with both deterministic test cases – considered by most of the literature – and stochastic executions. We utilize stochastic executions to define a domain-agnostic generic behavior space, tailored to policy testing. We compare QD-based policy testing to a state-of-the-art policy testing framework with two QD optimizers and three environments. Our evaluation assess fault detection, fault diversity and investigate the sensitivity of our method to the behavior space definition and the number of test executions. Our results show that QD improves fault diversity without significantly reducing fault discovery. Furthermore, QD optimization does not necessarily need domain knowledge and can adapt to generic behaviors with stochastic executions.
Zitieren
APA
Mazouni, Q., Gotlieb, A., Acher, M., & Spieker, H. (2026). Fault Diversity in Reinforcement Learning Policy Testing. ACM Transactions on Software Engineering and Methodology. https://doi.org/10.1145/3821533
Vancouver
Mazouni Q, Gotlieb A, Acher M, Spieker H. Fault Diversity in Reinforcement Learning Policy Testing. ACM Transactions on Software Engineering and Methodology. 2026. doi:10.1145/3821533
BibTeX
@article{Mazouni2026,
author = {Mazouni, Quentin and Gotlieb, Arnaud and Acher, Mathieu and Spieker, Helge},
title = {Fault Diversity in Reinforcement Learning Policy Testing},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
doi = {10.1145/3821533}
}
EUVIMED