Neural inverse optimal control for discrete-time impulsive systems

Impulsive systems describe processes with at least one state variable is impulsively changeable. The design of optimal control policies in impulsive systems is a complex task. In order to relax the solution for the Hamilton-Jacobi-Bellman equation, a meaningful cost functional can be proposed a posteriori in the inverse optimal problem. The main contribution of this paper is a neural inverse optimal control for discrete-time impulsive systems. Control policies for discrete-time impulsive systems are derived by combining inverse optimal control into a recurrent high order neural network (RHONN) trained with the Extended Kalman filter (EKF). The neural network avoids the development of a mathematical model to represent the studied system. For illustration, we apply the proposed neurocontrol to personalized drug treatment in influenza infection disease, whose nonlinear model is included and described for completeness. The robustness of the proposed framework is tested through Monte Carlo simulations.