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

被引：0

作者：

Luo, Biao ^{[1
]}

Liu, Derong ^{[2
]}

Huang, Tingwen ^{[3
]}

Li, Chao ^{[1
]}

机构：

[1] Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China

[2] Univ Sci & Technol Beijing, Sch Automat & Elect Engn, Beijing 100083, Peoples R China

[3] Texas A&M Univ Qatar, POB 23874, Doha, Qatar

来源：

NEURAL INFORMATION PROCESSING, ICONIP 2016, PT IV | 2016年 / 9950卷

关键词：

Optimal tracking control; Data-based; Q-learning; Critic-only; H-INFINITY CONTROL; LINEAR-SYSTEMS; CONTROL SCHEME; APPROXIMATION; ITERATION;

D O I：

10.1007/978-3-319-46681-1_68

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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.

引用

页码：573 / 581

页数：9

共 26 条

[1]

[Anonymous], IEEE T NEURAL NETW L

[2]

[Anonymous], 2013, REINFORCEMENT LEARNI

[3] Reinforcement learning in feedback control Challenges and benchmarks from technical process control [J].

Hafner, Roland ;

Riedmiller, Martin .

MACHINE LEARNING, 2011, 84 (1-2) :137-169

[4] UNIVERSAL APPROXIMATION OF AN UNKNOWN MAPPING AND ITS DERIVATIVES USING MULTILAYER FEEDFORWARD NETWORKS [J].

HORNIK, K ;

STINCHCOMBE, M ;

WHITE, H .

NEURAL NETWORKS, 1990, 3 (05) :551-560

[5] Approximate optimal trajectory tracking for continuous-time nonlinear systems [J].

Kamalapurkar, Rushikesh ;

Dinh, Huyen ;

Bhasin, Shubhendu ;

Dixon, Warren E. .

AUTOMATICA, 2015, 51 :40-48

[6] Optimal Tracking Control of Unknown Discrete-Time Linear Systems Using Input-Output Measured Data [J].

Kiumarsi, Bahare ;

Lewis, Frank L. ;

Naghibi-Sistani, Mohammad-Bagher ;

Karimpour, Ali .

IEEE TRANSACTIONS ON CYBERNETICS, 2015, 45 (12) :2770-2779

[7] Actor-Critic-Based Optimal Tracking for Partially Unknown Nonlinear Discrete-Time Systems [J].

Kiumarsi, Bahare ;

Lewis, Frank L. .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (01) :140-151

[8] Reinforcement Q-learning for optimal tracking control of linear discrete-time systems with unknown dynamics [J].

Kiumarsi, Bahare ;

Lewis, Frank L. ;

Modares, Hamidreza ;

Karimpour, Ali ;

Naghibi-Sistani, Mohammad-Bagher .

AUTOMATICA, 2014, 50 (04) :1167-1175

[9] Adaptive optimal control for a class of continuous-time affine nonlinear systems with unknown internal dynamics [J].

Liu, Derong ;

Yang, Xiong ;

Li, Hongliang .

NEURAL COMPUTING & APPLICATIONS, 2013, 23 (7-8) :1843-1850

[10] Reinforcement Learning Design-Based Adaptive Tracking Control With Less Learning Parameters for Nonlinear Discrete-Time MIMO Systems [J].

Liu, Yan-Jun ;

Tang, Li ;

Tong, Shaocheng ;

Chen, C. L. Philip ;

Li, Dong-Juan .

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (01) :165-176

← 1 2 3 →