Adaptive Dynamic Programming : Single and Multiple Controllers
Song, Ruizhuo
Adaptive Dynamic Programming : Single and Multiple Controllers by Ruizhuo Song, Qinglai Wei, Qing Li. - 1 recurso en línea (XV, 271 páginas) 126 ilustraciones,98 ilustraciones a color - Studies in Systems Decision and Control 166 2198-4182 Intelligent Technologies and Robotics (Springer-42732) .
Part I: Preparation -- Introduction to optimal control and adaptive dynamic programming -- Neural networks implementation -- Part II: Optimal control for system with single controller -- Finite-time optimal control -- Multi-objective optimal control -- Multiple actor-critic optimal control via ADP -- Optimal control for complex-valued nonlinear systems -- Chaotic systems optimal tracking control -- Part III: Multi-player systems games -- Optimal control for unknown systems with disturbances -- Zero-sum differential games -- Non-Zero-Sum games -- Synchronization control for multi-agent games.
This book presents a class of novel optimal control methods and games schemes based on adaptive dynamic programming techniques. For systems with one control input, the ADP-based optimal control is designed for different objectives, while for systems with multi-players, the optimal control inputs are proposed based on games. In order to verify the effectiveness of the proposed methods, the book analyzes the properties of the adaptive dynamic programming methods, including convergence of the iterative value functions and the stability of the system under the iterative control laws. Further, to substantiate the mathematical analysis, it presents various application examples, which provide reference to real-world practices.
9789811317125
10.1007/978-981-13-1712-5 doi
Programación dinámica
T57.83 / 2019 EB
Adaptive Dynamic Programming : Single and Multiple Controllers by Ruizhuo Song, Qinglai Wei, Qing Li. - 1 recurso en línea (XV, 271 páginas) 126 ilustraciones,98 ilustraciones a color - Studies in Systems Decision and Control 166 2198-4182 Intelligent Technologies and Robotics (Springer-42732) .
Part I: Preparation -- Introduction to optimal control and adaptive dynamic programming -- Neural networks implementation -- Part II: Optimal control for system with single controller -- Finite-time optimal control -- Multi-objective optimal control -- Multiple actor-critic optimal control via ADP -- Optimal control for complex-valued nonlinear systems -- Chaotic systems optimal tracking control -- Part III: Multi-player systems games -- Optimal control for unknown systems with disturbances -- Zero-sum differential games -- Non-Zero-Sum games -- Synchronization control for multi-agent games.
This book presents a class of novel optimal control methods and games schemes based on adaptive dynamic programming techniques. For systems with one control input, the ADP-based optimal control is designed for different objectives, while for systems with multi-players, the optimal control inputs are proposed based on games. In order to verify the effectiveness of the proposed methods, the book analyzes the properties of the adaptive dynamic programming methods, including convergence of the iterative value functions and the stability of the system under the iterative control laws. Further, to substantiate the mathematical analysis, it presents various application examples, which provide reference to real-world practices.
9789811317125
10.1007/978-981-13-1712-5 doi
Programación dinámica
T57.83 / 2019 EB