Value iteration for LQR control of unknown stochastic-parameter linear systems.
Wenwu FanJunlin XiongPublished in: Syst. Control. Lett. (2024)
Keyphrases
- closed loop
- linear systems
- linear quadratic
- control system
- pid controller
- control theory
- dynamical systems
- sufficient conditions
- linear equations
- control strategy
- state space
- fuzzy logic
- control method
- sparse linear systems
- markov decision processes
- dynamic programming
- reinforcement learning
- optimal control
- optimal policy
- coefficient matrix
- learning algorithm