Search

Online adaptive optimal control methods based on reinforcement learning algorithms typically need to check for the persistence of excitation condition, which is necessary to be known a priori for convergence of the algorithm. However, this condition is often infeasible to implement or monitor online. This paper proposes an online concurrent reinforcement learning algorithm (CRLA) based on neural networks (NNs) to solve the H ∞ control problem of partially unknown continuous-time systems, in which the need for persistence of excitation condition is relaxed by using the idea of concurrent learning. First, H ∞ control problem is formulated as a two-player zero-sum game, and then, online CRLA is employed to obtain the approximation of the optimal value and the Nash equilibrium of the game. The proposed algorithm is implemented on actor-critic-disturbance NN approximator structure to obtain the solution of the Hamilton-Jacobi-Isaacs equation online forward in time. During the implementation of the algorithm, the control input that acts as one player attempts to make the optimal control while the other player, that is, disturbance, tries to make the worst-case possible disturbance. Novel update laws are derived for adaptation of the critic and actor NN weights. The stability of the closed-loop system is guaranteed using Lyapunov technique, and the convergence to the Nash solution of the game is obtained. Simulation results show the effectiveness of the proposed method. Copyright © 2014 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

This paper develops a concurrent learning-based approximate dynamic programming (ADP) algorithm for solving the two-player zero-sum (ZS) game arising in H control of continuous-time (CT) systems with unknown nonlinear dynamics. First, the H control is formulated as a ZS game and then, an online algorithm is developed that learns the solution to the Hamilton-Jacobi-Isaacs (HJI) equation without using any knowledge on the system dynamics. This is achieved by using a neural network (NN) identifier to approximate the uncertain system dynamics. The algorithm is implemented on actor-critic-disturbance NN structure along with the NN identifier to approximate the optimal value function and the corresponding Nash solution of the game. All NNs are tuned at the same time. By using the idea of concurrent learning the need to check for the persistency of excitation condition is relaxed to simplified condition. The stability of the overall system is guaranteed and the convergence to the Nash solution of the game is shown. Simulation results show the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

In this paper, fuzzy-based closed-loop controller is applied to obtain a robust controller for blood glucose regulation in type I diabetes mellitus patients. The control technique incorporates expert knowledge about treatment of disease by using Mamdani-type fuzzy logic controller to robustly stabilize the blood glucose concentration in normoglycemic level. Controller performance is considered in terms of its ability to reject the multiple meals, on an averaged nonlinear patient model. Robustness of the controller is tested over a group of patients with model parameter varying considerably from the average model. The controller provides the possibility of more accurate control of blood glucose level in the patient in spite of uncertainty in model parameters and measurement noise. The proposed controller has showed superiority over other classical control techniques. A comparative study is presented with wellknown conventional H∞ control technique. Simulation results show the superiority of the proposed scheme in terms of reference tracking, disturbance rejection, and measurement noise in comparison with other approaches. [ABSTRACT FROM AUTHOR]