Data-Driven Adaptive Dynamic Programming for Optimal Control of Continuous-Time Multicontroller Systems With Unknown Dynamics

This paper investigates the optimal control of continuous-time multi-controller systems with completely unknown dynamics using data-driven adaptive dynamic programming (DD-ADP). In this investigation, all controllers take actions together as a team, and they have precisely same cost function, which is actually fully cooperative game. According to theory, HJB equation corresponding game derived. To obtain solution equation, model-based policy iteration (PI) algorithm first presented. On basis PI algorithm, DD-ADP without requiring system developed, neural networks (NNs) implementation scheme developed given. Stability convergence analysis are derived by Lyapunov theory. Finally, numerical simulation examples on linear nonlinear demonstrate effectiveness designed scheme.