Adaptive optimal control for a class of nonlinear partially uncertain dynamic systems via policy iteration

In this paper, by employing an online algorithm based on policy iteration (PI), an adaptive optimal control problem for continuous-time (CT) nonlinear partially uncertain dynamic systems is investigated. In this proposed algorithm, a discounted cost function is discussed, which is considered to be a more general case for optimal control problems. Two neural networks (NNs) are used to implement the algorithm, which aims at approximating the cost function and the control law, respectively. The uniform convergence to the optimal control is proven, and the stability of the system is guaranteed. An illustrating example is given.