Adaptive Dynamic Programming for a Class of Nonlinear Control Systems with General Separable Performance Index

Authors:
Qinglai Wei;Derong Liu;Huaguang Zhang
Affiliations:
School of Information Science and Engineering, Northeastern University, Shenyang, China;Department of Electrical and Computer Engineering, University of Illinois at Chicago, Chicago, USA;School of Information Science and Engineering, Northeastern University, Shenyang, China
Venue:
ISNN '08 Proceedings of the 5th international symposium on Neural Networks: Advances in Neural Networks, Part II
Year:
2008

Citing 7
Cited 2

New approach for nonseparable dynamic programming problems

Journal of Optimization Theory and Applications
A menu of designs for reinforcement learning over time

Neural networks for control
Adaptive critic designs: a case study for neurocontrol

Neural Networks
Neuro-Dynamic Programming

Neuro-Dynamic Programming
A new fuzzy identification method based on adaptive critic designs

ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
Adaptive differential dynamic programming for multiobjective optimal control

Automatica (Journal of IFAC)
A self-learning call admission control scheme for CDMA cellular networks

IEEE Transactions on Neural Networks

Finite horizon optimal tracking control for a class of discrete-time nonlinear systems

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part II
Self-learning control schemes for two-person zero-sum differential games of continuous-time nonlinear systems with saturating controllers

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an iterative scheme for a class of dynamic programming problem with general separable performance index has been studied. For the dynamic programming problem, the performance index function is time-varying and doesn't have the uniformed recurrent formulation. Noticing such prominent feature, adaptive dynamic programming (ADP) method is introduced. The proposed method aims to find out the efficient solution of the dynamic programming. Because of the approximation of the performance index, the optimal control can be computed forward-in-time. A proof is given to guarantee the convergence, and finally a case study shows the effectiveness of the proposed method.