Neural-network-based robust optimal control of uncertain nonlinear systems using model-free policy iteration algorithm.
Chao LiDing WangDerong LiuPublished in: IJCNN (2016)
Keyphrases
- optimal control
- nonlinear systems
- model free
- policy iteration
- control law
- reinforcement learning
- policy iteration algorithm
- lyapunov function
- adaptive control
- infinite horizon
- dynamic programming
- markov decision processes
- control problems
- linear matrix inequality
- policy evaluation
- hamilton jacobi bellman
- function approximation
- control strategy
- reinforcement learning algorithms
- approximate dynamic programming
- fuzzy controller
- actor critic
- fuzzy control
- learning rate
- neural network
- lyapunov stability
- rl algorithms
- fuzzy model
- fuzzy systems
- average reward
- tracking error
- real time
- policy gradient
- reinforcement learning methods
- temporal difference
- finite state
- data mining
- least squares
- optimal policy
- fixed point