Neuro-Dynamic Programming
Robust H∞ control for discrete-time fuzzy systems via basis-dependent Lyapunov functions
Information Sciences: an International Journal
Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence Proof
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Automatica (Journal of IFAC)
Online learning control by association and reinforcement
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
In this paper, constrained controller design is proposed for a class of nonlinear discrete-time uncertain system having matched type system uncertainties, using the solution of HJB (Hamilton-Jaccobi-Bellman) equation. The discrete-time HJB equation is formulated using a suitable nonquadratic term in the performance functional to tackle constraints on the control input. Based on the nonquadratic functional, a greedy HDP algorithm is used to obtain the constrained robust-optimal controller. The constrained robust controller requires knowledge of the upper bound of system uncertainties. For facilitating the implementation of the iterative algorithm, two neural networks are used to approximate the value function and to compute the optimal control policy, respectively. Their weights have been tuned using least squares method. Proposed algorithm has been applied on a nonlinear discrete-time system with matched uncertainties.