Optimal Control for Continuous-time Nonlinear Systems based on a Linear-like Policy Iteration.
Adnan TahirovicAlessandro AstolfiPublished in: CDC (2019)
Keyphrases
- optimal control
- nonlinear systems
- policy iteration
- control law
- lyapunov function
- lyapunov stability
- infinite horizon
- adaptive control
- dynamic programming
- control strategy
- control problems
- actor critic
- reinforcement learning
- approximate dynamic programming
- optimal control problems
- hamilton jacobi bellman
- fuzzy model
- fuzzy controller
- markov decision processes
- fuzzy control
- brownian motion
- average cost
- optimal policy
- learning rate
- average reward
- linear matrix inequality
- tracking error
- neural network
- fuzzy systems
- fixed point
- control scheme
- input output
- model free