Costate-Supplement ADP for Model-Free Optimal Control of Discrete-Time Nonlinear Systems.
Jun YeYougang BianBiao LuoManjiang HuBiao XuRongjun DingPublished in: IEEE Trans. Neural Networks Learn. Syst. (2024)
Keyphrases
- model free
- optimal control
- nonlinear systems
- control law
- optimal control problems
- reinforcement learning
- dead zone
- adaptive control
- linear quadratic
- lyapunov function
- control problems
- function approximation
- reinforcement learning algorithms
- adaptive neural
- dynamic programming
- control strategy
- feedback control
- fuzzy control
- infinite horizon
- temporal difference
- state space
- markov chain
- learning rate
- policy iteration
- fuzzy model
- fuzzy controller
- nonlinear equations
- machine learning
- fuzzy systems
- control method
- learning algorithm
- closed loop
- sliding mode
- finite state
- average cost
- average reward
- optimal policy
- impedance control
- markov decision processes
- input output
- dynamic environments
- control system
- lyapunov stability
- data mining