Local Policy Iteration Adaptive Dynamic Programming for Discrete-Time Nonlinear Systems.
Qinglai WeiYancai XuQiao LinDerong LiuRuizhuo SongPublished in: ISNN (2) (2017)
Keyphrases
- nonlinear systems
- policy iteration
- markov decision processes
- dynamic programming
- adaptive control
- adaptive neural
- reinforcement learning
- optimal policy
- finite state
- dead zone
- optimal control
- control law
- infinite horizon
- markov decision problems
- fuzzy model
- model free
- approximate dynamic programming
- fuzzy control
- average reward
- fuzzy systems
- fuzzy controller
- fixed point
- state space
- markov decision process
- linear programming
- control problems
- actor critic
- temporal difference
- learning rate
- least squares
- neural network
- markov chain
- fuzzy logic
- control method
- function approximation
- input output
- average cost
- control algorithm