Détail du document
Identifiant
oai:arXiv.org:2408.15150
Sujet
Computer Science - Software Engine...Auteur
Thomas, Deepak-George Biagiola, Matteo Humbatova, Nargiz Wardat, Mohammad Jahangirova, Gunel Rajan, Hridesh Tonella, PaoloCatégorie
Computer Science
Année
2024
Date de référencement
04/09/2024
Mots clés
rl muprlRésumé
Reinforcement Learning (RL) is increasingly adopted to train agents that can deal with complex sequential tasks, such as driving an autonomous vehicle or controlling a humanoid robot.
Correspondingly, novel approaches are needed to ensure that RL agents have been tested adequately before going to production.
Among them, mutation testing is quite promising, especially under the assumption that the injected faults (mutations) mimic the real ones.
In this paper, we first describe a taxonomy of real RL faults obtained by repository mining.
Then, we present the mutation operators derived from such real faults and implemented in the tool muPRL.
Finally, we discuss the experimental results, showing that muPRL is effective at discriminating strong from weak test generators, hence providing useful feedback to developers about the adequacy of the generated test scenarios.
;Comment: Accepted at ICSE '25
Thomas, Deepak-George,Biagiola, Matteo,Humbatova, Nargiz,Wardat, Mohammad,Jahangirova, Gunel,Rajan, Hridesh,Tonella, Paolo, 2024, muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults
Machine learning and EEG can classify passive viewing of discrete categories of visual stimuli but not the observation of pain
eeg classify neutral ml participants non-pain expressions images scenes pain
