Multistep Look-Ahead Policy Iteration for Optimal Control of Discrete-Time Nonlinear Systems With Isoperimetric Constraints.
Tao LiQinglai WeiFei-Yue WangPublished in: IEEE Trans. Syst. Man Cybern. Syst. (2024)
Keyphrases
- optimal control
- nonlinear systems
- policy iteration
- control law
- optimal control problems
- lyapunov function
- infinite horizon
- adaptive control
- control strategy
- control problems
- dead zone
- dynamic programming
- hamilton jacobi bellman
- feedback control
- reinforcement learning
- fuzzy controller
- actor critic
- markov decision processes
- finite state
- average cost
- lyapunov stability
- fuzzy systems
- fuzzy control
- fuzzy model
- approximate dynamic programming
- markov chain
- optimal policy
- control scheme
- tracking error
- fixed point
- control algorithm
- control method
- average reward
- sufficient conditions
- evaluation function
- state space
- control system
- data mining