Data-Based Optimal Tracking Control of Nonaffine Nonlinear Discrete-Time Systems Conference Paper

abstract

• Springer International Publishing AG 2016. The optimal tracking control problem of nonaffine nonlinear discrete-time systems is considered in this paper. The problem relies on the solution of the so-called tracking Hamilton-Jacobi-Bellman equation, which is extremely difficult to be solved even for simple systems. To overcome this difficulty, the data-based Q-learning algorithm is proposed by learning the optimal tracking control policy from data of the practical system. For its implementation purpose, the critic-only neural network structure is developed, where only critic neural network is required to estimate the Q-function and the least-square scheme is employed to update the weight of neural network.

authors

• Huang, Tingwen

published proceedings

• NEURAL INFORMATION PROCESSING, ICONIP 2016, PT IV

author list (cited authors)

• Luo, B., Liu, D., Huang, T., & Li, C.

citation count

• 0

complete list of authors

• Luo, Biao||Liu, Derong||Huang, Tingwen||Li, Chao

publication date

• January 2016

publisher

• Springer Nature  Publisher

published in

• Lecture Notes in Computer Science  Journal

keywords

• Critic-only
• Data-based
• Optimal Tracking Control
• Q-learning

Digital Object Identifier (DOI)

• 10.1007/978-3-319-46681-1_68

International Standard Book Number (ISBN) 13

• 978-3-319-46680-4

start page

• 573

end page

• 581

volume

• 9950

URL

• http://dx.doi.org/10.1007/978-3-319-46681-1_68