Self-learning optimal control of nonlinear systems. Adaptive dynamic programming approach
Chaos control for problems involving ordinary differential equations (34H10) Research exposition (monographs, survey articles) pertaining to calculus of variations and optimal control (49-02) Dynamic programming in optimal control and differential games (49L20) Applications of optimal control and differential games (49N90) Learning and adaptive systems in artificial intelligence (68T05) Multi-objective and goal programming (90C29) Dynamic programming (90C39) Discrete-time control/observation systems (93C55)
In this book, based on Adaptive Dynamic Programming (ADP) techniques, which quantitatively obtain the optimal control schemes of the systems, a class of novel, self-learning, optimal control schemes is investigated. The book contains ten chapters. The first chapter includes the basic principles for ADP algorithms. Chapter 2 proposes a finite horizon iterative ADP algorithm in order to solve the optimal control problem associated with a class of discrete-time nonlinear systems. The next three chapters develop Q-learning algorithms. Chapters 6 and 7 investigate discrete-time nonlinear systems with general multi-objective performance index functions. Chapter 8 is focused on continuous-time chaotic systems and in Chapter 9 estimates the optimal tracking control of unknown chaotic systems. Finally, Chapter 10 develops a new ADP-based sensor scheduling scheme. The present book contains various real-world examples to illustrate the developed mathematical analysis. Thus, it is a valuable and important guide for engineers, researchers, and students in systems, decision and control science.
- Adaptive dynamic programming and optimal control of nonlinear nonaffine systems
- Adaptive learning control for a class of nonlinearly parameterized systems
- Self-learning robust optimal control for continuous-time nonlinear systems with mismatched disturbances
- Optimal control for nonlinear systems based on lazy learning
- Adaptive learning control for feedback linearizable systems
- Adaptive dynamic programming with applications in optimal control
- Adaptive Optimal Feedback Control with Learned Internal Dynamics Models
- scientific article; zbMATH DE number 970345
- An adaptive learning control of nonlinear systems with iteration-varying trajectory
- Reinforcement learning for adaptive optimal control of unknown continuous-time nonlinear systems with input constraints
- Adaptive critic control with robust stabilization for uncertain nonlinear systems
- Output feedback reinforcement learning control for linear systems
- Adaptive Optimal Feedback Control with Learned Internal Dynamics Models
- Robust adaptive dynamic programming
- Adaptive dynamic programming: single and multiple controllers
- Deep reinforcement learning with guaranteed performance. A Lyapunov-based approach
- Optimal adaptive control and differential games by reinforcement learning principles
- Advanced Optimal Control and Applications Involving Critic Intelligence
- Predictive Learning Control for Unknown Nonaffine Nonlinear Systems
- A New Integral Critic Learning for Optimal Tracking Control with Applications to Boiler‐Turbine Systems
- Online and hard constrained adaptive dynamic programming algorithm for energy storage control in smart buildings
- Dual heuristic programming with just‐in‐time modeling for self‐learning fault‐tolerant control of mobile robots
- Sequential intelligent dynamic system modeling and control
- Q-learning based tracking control with novel finite-horizon performance index
- Combined use of dynamic inversion and reinforcement learning for optimal adaptive control of supersonic transport airplane motion
- A new self-learning optimal control laws for a class of discrete-time nonlinear systems based on ESN architecture
This page was built for publication: Self-learning optimal control of nonlinear systems. Adaptive dynamic programming approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1635523)
