Paper Info
Title
Generalized Policy Iteration Adaptive Dynamic Programming for Discrete-Time Nonlinear Systems
Abstract
This paper is concerned with a novel generalized policy iteration algorithm for solving optimal control problems for discrete-time nonlinear systems. The idea is to use an iterative adaptive dynamic programming algorithm to obtain iterative control laws which make the iterative value functions converge to the optimum. Initialized by an admissible control law, it is shown that the iterative value functions are monotonically nonincreasing and converge to the optimal solution of Hamilton-Jacobi-Bellman equation, under the assumption that a perfect function approximation is employed. The admissibility property is analyzed, which shows that any of the iterative control laws can stabilize the nonlinear system. Neural networks are utilized to implement the generalized policy iteration algorithm, by approximating the iterative value function and computing the iterative control law, respectively, to achieve approximate optimal control. Finally, numerical examples are presented to verify the effectiveness of the present generalized policy iteration algorithm.
Year
DOI
Venue
2015
10.1109/TSMC.2015.2417510
Systems, Man, and Cybernetics: Systems, IEEE Transactions
Keywords
DocType
Volume
Neural networks,Optimal control,Learning (artificial intelligence),Dynamic programming,Nonlinear systems
Journal
PP
Issue
ISSN
Citations 
99
2168-2216
23
PageRank 
References 
Authors
0.78
57
3
Name
Order
Citations
PageRank
Derong Liu15457286.88
Qinglai Wei22494110.44
Pengfei Yan31484.82