Adaptive optimal control algorithm for continuous-time nonlinear systems based on policy iteration.
Draguna L. VrabieFrank L. LewisPublished in: CDC (2008)
Keyphrases
- nonlinear systems
- control algorithm
- control law
- optimal control
- adaptive fuzzy
- policy iteration
- adaptive control
- control strategy
- control method
- fuzzy controller
- adaptive neural
- control system
- actor critic
- tracking error
- lyapunov stability
- infinite horizon
- markov decision processes
- approximate dynamic programming
- reinforcement learning
- lyapunov function
- dynamic programming
- inverted pendulum
- controller design
- fuzzy control
- average reward
- model free
- closed loop
- average cost
- optimal policy
- control scheme
- markov chain
- sliding mode
- neural network
- fuzzy systems
- real time
- fuzzy model
- finite state
- mathematical model
- state space
- linear model
- dynamical systems
- pi controller