Online Adaptive Policy Learning Algorithm for $H_{\infty }$ State Feedback Control of Unknown Affine Nonlinear Discrete-Time Systems

Abstract

The problem of H∞ state feedback control of affine nonlinear discrete-time systems with unknown dynamics is investigated in this paper. An online adaptive policy learning algorithm (APLA) based on adaptive dynamic programming (ADP) is proposed for learning in real-time the solution to the Hamilton-Jacobi-Isaacs (HJI) equation, which appears in the H∞ control problem. In the proposed algorithm, three neural networks (NNs) are utilized to find suitable approximations of the optimal value function and the saddle point feedback control and disturbance policies. Novel weight updating laws are given to tune the critic, actor, and disturbance NNs simultaneously by using data generated in real-time along the system trajectories. Considering NN approximation errors, we provide the stability analysis of the proposed algorithm with Lyapunov approach. Moreover, the need of the system input dynamics for the proposed algorithm is relaxed by using a NN identification scheme. Finally, simulation examples show the effectiveness of the proposed algorithm.

Asynchronous Piecewise Output-Feedback Control for Large-Scale Fuzzy Systems via Distributed Event-Triggering Schemes

“…Finally, a class of practical large-scale nonlinear system in the area of power systems has been employed to demonstrate the effectiveness of the proposed control approaches. One interesting future research topic is the extension of the proposed methods to adaptive policy learning algorithm as shown in [62] for the large-scale fuzzy systems with event-triggering control.…”

Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration

“…In [15][16][17][18][19], the integral reinforcement learning algorithm was used to solve optimal control problems of continuous-time nonlinear systems. Hamilton-Jacobi-Bellman (HJB) equation is one of the important keys in optimal control problems [14,20]. In linear time-invariant systems, the HJB becomes the Riccati equation, which can be solved effectively.…”

Global mutual information-based feature selection approach using single-objective and multi-objective optimization

“…With the development of data acquisition and storage technology, high-dimensional data widely exist in nature [1], finance [2], industry [3][4][5], biomedicine [6][7][8] and many other fields, which contain complicated nonlinear relationship among multiple features. Finding potential useful information and building prediction model from high-dimensional data have become one of the most important aspects of data mining and knowledge discovery [9].…”