Integrating safety constraints into adversarial training for robust deep reinforcement learning
Jinling Meng, Fei Zhu, Yangyang Ge, Peiyao Zhao
Topics & Concepts
Reinforcement learningAdversarial systemMarkov decision processComputer scienceRobustness (evolution)Artificial intelligenceGeneralizationMathematical optimizationMachine learningMarkov processMathematicsMathematical analysisStatisticsGeneChemistryBiochemistryAdversarial Robustness in Machine LearningSmart Grid Security and Resilience