Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems With Trajectory-Based Initial Control Policy.
Jiahui XuJingcheng WangJun RaoShunyu WuYanjiu ZhongPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- optimal control
- nonlinear systems
- dynamic programming
- control law
- control policy
- adaptive control
- optimal control problems
- average cost
- reinforcement learning
- approximate dynamic programming
- lyapunov function
- adaptive neural
- adaptive fuzzy
- control problems
- linear quadratic
- infinite horizon
- feedback control
- dead zone
- tracking error
- hamilton jacobi bellman
- long run
- linear programming
- control strategy
- optimal policy
- multistage
- state space
- control policies
- brownian motion
- markov decision processes
- actor critic
- nonlinear equations
- fuzzy control
- fuzzy model
- markov chain
- sliding mode
- fuzzy controller
- lyapunov stability
- evolutionary computation