Adaptive dynamic programming for discrete-time systems with infinite horizon and Ɛ -error bound in the performance cost

Authors:
Derong Liu;Ning Jin
Affiliations:
Key Laboratory of Complex Systems and Intelligence Science, Chinese Academy of Sciences, Beijing, P. R. China;Department of Electrical and Computer Engineering, University of Illinois, Chicago, IL
Venue:
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Year:
2009

Citing 9
Cited 2

Building and understanding adaptive systems: a statistical/numerical approach to factory automation and brain research

IEEE Transactions on Systems, Man and Cybernetics
A menu of designs for reinforcement learning over time

Neural networks for control
Neuro-Dynamic Programming

Neuro-Dynamic Programming
Art and Theory of Dynamic Programming

Art and Theory of Dynamic Programming
Adaptive dynamic programming

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Nearly optimal control laws for nonlinear systems with saturating actuators using a neural network HJB approach

Automatica (Journal of IFAC)
Adaptive critic designs

IEEE Transactions on Neural Networks
Online learning control by association and reinforcement

IEEE Transactions on Neural Networks
A self-learning call admission control scheme for CDMA cellular networks

IEEE Transactions on Neural Networks

A three-network architecture for on-line learning and optimization based on adaptive dynamic programming

Neurocomputing
Optimal control of unknown nonaffine nonlinear discrete-time systems based on adaptive dynamic programming

Automatica (Journal of IFAC)

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present our work on infinite horizon adaptive dynamic programming problem, which is referred to as Ɛ -adaptive dynamic programming, for discrete-time systems with discount factor 0 Ɛ *, which is determined from an Ɛ -optimal cost VƐ *, is obtained to approximate the optimal controller. The Ɛ -optimal controller µƐ * can always control the state to approach the equilibrium state, while the performance cost is close to the biggest lower bound of all performance costs within an error according to E. An algorithm for finding the Ɛ -optlmal controller is developed and numerical experiments are given to illustrate the performance of the algorithm.