Adaptive optimal control for continuous-time linear systems based on policy iteration.
Draguna L. VrabieOctavian C. PastravanuMurad Abu-KhalafFrank L. LewisPublished in: Autom. (2009)
Keyphrases
- optimal control
- linear systems
- policy iteration
- infinite horizon
- actor critic
- dynamic programming
- control problems
- reinforcement learning
- dynamical systems
- sufficient conditions
- approximate dynamic programming
- optimal control problems
- average cost
- control strategy
- markov decision processes
- control theory
- average reward
- sparse linear systems
- control law
- markov decision process
- model free
- markov decision problems
- policy iteration algorithm
- temporal difference
- interior point methods
- finite state
- convex optimization
- least squares
- real time