A neural-network-based iterative GDHP approach for solving a class of nonlinear optimal control problems with control constraints

• Published in: Neural computing & applications Vol. 22; no. 2; pp. 219 - 227
• Main Authors: Wang, Ding, Liu, Derong, Zhao, Dongbin, Huang, Yuzhu, Zhang, Dehua
• Format: Journal Article
• Language: English
• Published: London Springer-Verlag 01.02.2013
• Subjects: Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Image Processing and Computer Vision; Isnn 2011; Probability and Statistics in Computer Science; Adaptive dynamic programming; Neural networks; Optimal control; Neural dynamic programming; Reinforcement learning; Approximate dynamic programming; Adaptive critic designs
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-011-0707-2

In this paper, a novel neural-network-based iterative adaptive dynamic programming (ADP) algorithm is proposed. It aims at solving the optimal control problem of a class of nonlinear discrete-time systems with control constraints. By introducing a generalized nonquadratic functional, the iterative ADP algorithm through globalized dual heuristic programming technique is developed to design optimal controller with convergence analysis. Three neural networks are constructed as parametric structures to facilitate the implementation of the iterative algorithm. They are used for approximating at each iteration the cost function, the optimal control law, and the controlled nonlinear discrete-time system, respectively. A simulation example is also provided to verify the effectiveness of the control scheme in solving the constrained optimal control problem.