Finite-horizon optimal control for continuous-time uncertain nonlinear systems using reinforcement learning

International Journal of Systems Science ◽

10.1080/00207721.2020.1797223 ◽

2020 ◽

Vol 51 (13) ◽

pp. 2429-2440

Author(s):

Jingang Zhao ◽

Minggang Gan

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Nonlinear Systems ◽

Continuous Time ◽

Finite Horizon ◽

Uncertain Nonlinear Systems

Download Full-text

Two‐loop reinforcement learning algorithm for finite‐horizon optimal control of continuous‐time affine nonlinear systems

International Journal of Robust and Nonlinear Control ◽

10.1002/rnc.5826 ◽

2021 ◽

Author(s):

Zhe Chen ◽

Wenqian Xue ◽

Ning Li ◽

Frank L. Lewis

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Nonlinear Systems ◽

Continuous Time ◽

Learning Algorithm ◽

Finite Horizon ◽

Affine Nonlinear Systems ◽

Reinforcement Learning Algorithm

Download Full-text

Reinforcement Learning and Adaptive Optimal Control for Continuous-Time Nonlinear Systems: A Value Iteration Approach

IEEE Transactions on Neural Networks and Learning Systems ◽

10.1109/tnnls.2020.3045087 ◽

2021 ◽

pp. 1-10

Author(s):

Tao Bian ◽

Zhong-Ping Jiang

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Nonlinear Systems ◽

Continuous Time ◽

Value Iteration ◽

Adaptive Optimal Control ◽

Download Full-text

Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints

International Journal of Control ◽

10.1080/00207179.2013.848292 ◽

2013 ◽

Vol 87 (3) ◽

pp. 553-566 ◽

Author(s):

Xiong Yang ◽

Derong Liu ◽

Ding Wang

Keyword(s):

Optimal Control ◽

Reinforcement Learning ◽

Nonlinear Systems ◽

Continuous Time ◽

Input Constraints ◽

Adaptive Optimal Control

Download Full-text

Reinforcement-Learning-Based Robust Controller Design for Continuous-Time Uncertain Nonlinear Systems Subject to Input Constraints

IEEE Transactions on Cybernetics ◽

10.1109/tcyb.2015.2417170 ◽

2015 ◽

Vol 45 (7) ◽

pp. 1372-1385 ◽

Author(s):

Derong Liu ◽

Xiong Yang ◽

Ding Wang ◽

Qinglai Wei

Keyword(s):

Reinforcement Learning ◽

Nonlinear Systems ◽

Continuous Time ◽

Controller Design ◽

Uncertain Nonlinear Systems ◽

Input Constraints ◽

Robust Controller ◽

Robust Controller Design

Download Full-text

Continuous-time synthesizing robust sampled-data dynamic output-feedback controllers for uncertain nonlinear systems in Takagi–Sugeno form: A descriptor representation approach

Information Sciences ◽

10.1016/j.ins.2021.02.032 ◽

2021 ◽

Author(s):

Jaejun Lee ◽

Ji Hyun Moon ◽

Ho Jae Lee

Keyword(s):

Nonlinear Systems ◽

Output Feedback ◽

Continuous Time ◽

Dynamic Output Feedback ◽

Uncertain Nonlinear Systems ◽

Sampled Data ◽

Feedback Controllers ◽

Dynamic Output ◽

Download Full-text

Solving Finite-Horizon HJB for Optimal Control of Continuous-Time Systems

2021 International Conference on Computer, Control and Robotics (ICCCR) ◽

10.1109/icccr49711.2021.9349412 ◽

2021 ◽

Author(s):

Ziyu Lin ◽

Jingliang Duan ◽

Shengbo Eben Li ◽

Jie Li ◽

Haitong Ma ◽

...

Keyword(s):

Optimal Control ◽

Continuous Time ◽

Finite Horizon ◽

Continuous Time Systems ◽

Download Full-text

A novel actor–critic–identifier architecture for approximate optimal control of uncertain nonlinear systems

10.1016/j.automatica.2012.09.019 ◽

2013 ◽

Vol 49 (1) ◽

pp. 82-92 ◽

Author(s):

S. Bhasin ◽

R. Kamalapurkar ◽

M. Johnson ◽

K.G. Vamvoudakis ◽

F.L. Lewis ◽

...

Keyword(s):

Optimal Control ◽

Nonlinear Systems ◽

Uncertain Nonlinear Systems

Download Full-text

Neural-network-based robust optimal control design for a class of uncertain nonlinear systems via adaptive dynamic programming

Information Sciences ◽

10.1016/j.ins.2014.05.050 ◽

2014 ◽

Vol 282 ◽

pp. 167-179 ◽

Author(s):

Ding Wang ◽

Derong Liu ◽

Hongliang Li ◽

Hongwen Ma

Keyword(s):

Neural Network ◽

Optimal Control ◽

Dynamic Programming ◽

Nonlinear Systems ◽

Control Design ◽

Adaptive Dynamic Programming ◽

Uncertain Nonlinear Systems ◽

Robust Optimal Control ◽

Adaptive Dynamic

Download Full-text

HIGHER ORDER SLIDING MODE CONTROL FOR CONTINUOUS TIME NONLINEAR SYSTEMS BASED ON OPTIMAL CONTROL

Proceedings of the 6th International Conference on Informatics in Control, Automation and Robotics ◽

10.5220/0002168100540059 ◽

2009 ◽

Keyword(s):

Optimal Control ◽

Nonlinear Systems ◽

Sliding Mode Control ◽

Continuous Time ◽

Sliding Mode ◽

Higher Order ◽

Download Full-text

Approximate Finite-Horizon Optimal Control for Input-Affine Nonlinear Systems with Input Constraints

IFAC Proceedings Volumes ◽

10.3182/20130904-3-fr-2041.00037 ◽

2013 ◽

Vol 46 (23) ◽

pp. 199-204

Author(s):

G. Scarciotti ◽

A. Astolfi

Keyword(s):

Optimal Control ◽

Nonlinear Systems ◽

Finite Horizon ◽

Input Constraints ◽

Affine Nonlinear Systems

Download Full-text