Secure Q-Learning of Fuzzy Markov Jump Systems Under Malicious Attacks: A Homotopic Scheme

This article proposes a novel reinforcement learning (RL)-based secure control policy for nonlinear Markov jump systems (MJSs) subject to false data injection attacks (FDIAs). First, the Takagi-Sugeno (T-S) fuzzy model is applied to describe the nonlinear MJS. A min-max strategy and an off-policy homotopic Q-learning (HQ) scheme are then introduced to design a secure control policy without requiring knowledge of the system dynamics. The proposed approach offers two main advantages: it does not require an initial stabilizing control gain, and it guarantees unbiased learning under persistently excited conditions. Furthermore, a rigorous stability analysis of the overall closed-loop system under FDIAs is presented. Finally, the effectiveness of the proposed approach is demonstrated using a tunnel diode circuit.