Reinforcement Learning-Based Control of Nonlinear Systems Using Lyapunov Stability Concept and Fuzzy Reward Scheme.
Ming ChenHak-Keung LamQian ShiBo XiaoPublished in: IEEE Trans. Circuits Syst. II Express Briefs (2020)
Keyphrases
- lyapunov stability
- nonlinear systems
- reinforcement learning
- adaptive control
- actor critic
- lyapunov function
- optimal control
- adaptive fuzzy
- control law
- tracking error
- stability analysis
- controller design
- control problems
- adaptive neural
- inverted pendulum
- policy gradient
- feedback control
- fuzzy controller
- chaotic systems
- sliding mode
- control system
- fuzzy systems
- variable structure
- takagi sugeno
- function approximation
- reinforcement learning algorithms
- state space
- fuzzy model
- fuzzy control
- control method
- control strategy
- markov decision processes
- learning algorithm
- control algorithm
- approximate dynamic programming
- machine learning
- learning rate
- neural network
- reward function
- temporal difference
- model free
- control scheme
- closed loop
- fuzzy logic
- fuzzy logic controller
- gradient method
- membership functions
- input output
- optimal policy
- genetic algorithm