Decentralized Optimal Neurocontroller Design for Mismatched Interconnected Systems via Integral Policy Iteration

In this brief, the decentralized optimal control problem of continuous-time input-affine nonlinear systems with mismatched interconnections is investigated by utilizing data-based integral policy iteration. Initially, the decentralized mismatched subsystems are converted into the nominal auxiliary subsystems. Then, we derive the optimal controllers of the nominal auxiliary subsystems with a well-defined discounted cost function under the framework of adaptive dynamic programming. In the implementation process, the integral reinforcement learning algorithm is employed to explore the partially or completely unknown system dynamics. It is worth mentioning that the actor-critic structure is adopted based on neural networks, in order to evaluate the control policy and the performance of the control system. Besides, the least squares method is also involved in this online learning process. Finally, a simulation example is provided to illustrate the validity of the developed algorithm.