Adaptive Control and Regret Minimization in Linear Quadratic Gaussian (LQG) Setting.
Sahin LaleKamyar AzizzadenesheliBabak HassibiAnima AnandkumarPublished in: ACC (2021)
Keyphrases
- linear quadratic
- adaptive control
- control law
- closed loop
- regret minimization
- optimal control
- dynamical systems
- vector valued
- control method
- control system
- gaussian model
- control scheme
- nash equilibrium
- reinforcement learning
- dynamic environments
- game theoretic
- dynamic programming
- control algorithm
- control strategy
- multi modal