A Generalized Policy Iteration Adaptive Dynamic Programming Algorithm for Optimal Control of Discrete-Time Nonlinear Systems with Actuator Saturation.
Qiao LinQinglai WeiBo ZhaoPublished in: ISNN (2) (2017)
Keyphrases
- optimal control
- nonlinear systems
- policy iteration
- control law
- optimal control problems
- dead zone
- adaptive control
- control strategy
- control method
- adaptive neural
- lyapunov function
- infinite horizon
- control problems
- reinforcement learning
- actor critic
- tracking error
- dynamic programming
- feedback control
- control system
- hamilton jacobi bellman
- approximate dynamic programming
- markov decision processes
- fuzzy controller
- average reward
- average cost
- closed loop
- fuzzy control
- fuzzy systems
- fuzzy model
- sliding mode
- learning rate
- stochastic control
- model free
- optimal policy
- neural network
- control algorithm
- learning algorithm
- finite state