Relaxed Actor-Critic With Convergence Guarantees for Continuous-Time Optimal Control of Nonlinear Systems.
Jingliang DuanJie LiQiang GeShengbo Eben LiMonimoy BujarbaruahFei MaDezhao ZhangPublished in: IEEE Trans. Intell. Veh. (2023)
Keyphrases
- optimal control
- actor critic
- lyapunov stability
- nonlinear systems
- control law
- lyapunov function
- control strategy
- control problems
- tracking error
- dynamic programming
- adaptive control
- stability analysis
- policy gradient
- feedback control
- reinforcement learning
- fuzzy controller
- infinite horizon
- adaptive fuzzy
- adaptive neural
- fuzzy control
- fuzzy systems
- policy iteration
- convergence rate
- dynamic environments
- data mining
- hamilton jacobi bellman
- learning rate
- sufficient conditions