XCS as a reinforcement learning approach to automatic test case prioritization

Rosenbauer, Lukas; Stein, Anthony; Maier, Roland; Pätzel, David; Hähner, Jörg

doi:10.1145/3377929.3398128

Cited by 20 publications

(25 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to be consistent with the previous literature, we follow the notation of Rosenbauer et al (2020).…”

Section: Problem Descriptionmentioning

confidence: 99%

“…The action space for both our XCSF-based solution as well as the network of Spieker et al 2017is R whereas the XCS-based agent of Rosenbauer et al (2020) used an action space of {0, 1, . .…”

Section: Problem Descriptionmentioning

confidence: 99%

“…The task of selecting such a prioritization and test suite optimally is referred to as adaptive test case selection problem (ATCS) (Spieker et al, 2017). Spieker et al (2017) and Rosenbauer et al (2020) exploit the fact that the CI infrastructure saves the testing history (duration of tests, executions, test results). This information is used to construct a prioritization of the test cases.…”

Section: Introductionmentioning

confidence: 99%

“…An agent either gets a penalty or a reward, based on the outcome of the execution and the determined prioritization. Spieker et al (2017) employ a neural network-based agent while Rosenbauer et al (2020) utilize one based on the XCS classifier system (XCS) (Wilson, 1995).…”

Section: Introductionmentioning

confidence: 99%

“…This is followed by a description of how XCSF evolved from XCS and how we adapted it for ATCS (Section 5). We benchmark our XCSF-based agent on three industrial data sets against the neural network of Spieker et al (2017) and the XCS of Rosenbauer et al (2020) in Section 6. We discuss possible future work in Section 7.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

XCSF for Automatic Test Case Prioritization

Rosenbauer

Stein

Pätzel

et al. 2020

Proceedings of the 12th International Joint Conference on Computational Intelligence

Self Cite

View full text Add to dashboard Cite

Testing is a crucial part in the development of a new product. Due to the change from manual testing to automated testing, companies can rely on a higher number of tests. There are certain cases such as smoke tests where the execution of all tests is not feasible and a smaller test suite of critical test cases is necessary. This prioritization problem has just gotten into the focus of reinforcement learning. A neural network and an XCS classifier system have been applied to this task. Another evolutionary machine learning approach is the XCSF which produces, unlike XCS, continuous outputs. In this work we show that XCSF is superior to both the neural network and XCS for this problem.

show abstract

“…In order to be consistent with the previous literature, we follow the notation of Rosenbauer et al (2020).…”

Section: Problem Descriptionmentioning

confidence: 99%

Section: Problem Descriptionmentioning

confidence: 99%