A novel optimal tracking control scheme for a class of discrete-time nonlinear systems using generalised policy iteration adaptive dynamic programming algorithm.
Qiao LinQinglai WeiDerong LiuPublished in: Int. J. Syst. Sci. (2017)
Keyphrases
- dynamic programming
- nonlinear systems
- adaptive neural control
- control scheme
- tracking error
- markov decision processes
- policy iteration
- control law
- optimal solution
- optimal policy
- optimal control
- optimization algorithm
- learning algorithm
- adaptive fuzzy
- controller design
- fuzzy controller
- convergence rate
- learning rate
- reinforcement learning
- model free
- adaptive control
- actor critic
- average reward
- state space
- infinite horizon
- search space
- machine learning
- stability analysis
- fuzzy systems
- least squares
- neural network
- closed loop
- sufficient conditions
- basis functions
- input output