Integrating safety constraints into adversarial training for robust deep reinforcement learning

DOI10.1016/J.INS.2022.11.051MaRDI QIDQ6132002zbMATH OpenFDO

Authors Jinling Meng, Fei Zhu, Yangyang Ge, Peiyao Zhao

Publication date 18 April 2024

Published in Information Sciences (Search for Journal in Brave)

zbMATH Keywords

reinforcement learningconstrained Markov decision processpenalty function methodadversarial trainingrobust deep reinforcement learning

Mathematics Subject Classification ID

Computer science (68-XX) Operations research, mathematical programming (90-XX)

This page was built for publication: Integrating safety constraints into adversarial training for robust deep reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6132002)