Off-policy neuro-optimal control for unknown complex-valued nonlinear systems based on policy iteration.
Ruizhuo SongQinglai WeiWendong XiaoPublished in: Neural Comput. Appl. (2017)
Keyphrases
- optimal control
- nonlinear systems
- complex valued
- policy iteration
- control law
- real valued
- infinite horizon
- adaptive control
- recurrent neural networks
- control problems
- control strategy
- dynamic programming
- hamilton jacobi bellman
- neural network
- reinforcement learning
- fuzzy model
- actor critic
- markov decision processes
- average reward
- activation function
- approximate dynamic programming
- artificial neural networks
- fuzzy controller
- neuro fuzzy
- fuzzy systems
- fuzzy control
- average cost
- learning rate
- mathematical model
- optimal policy
- fuzzy neural network
- hidden layer
- control algorithm
- fuzzy rules
- back propagation
- decision making