A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization.
Kai DuQingxin MengFu ZhangPublished in: SIAM J. Control. Optim. (2022)
Keyphrases
- linear quadratic
- optimal control
- gaussian model
- learning algorithm
- closed loop
- dynamical systems
- vector valued
- machine learning
- control system
- training data
- expectation maximization
- dynamic programming
- control strategy
- reinforcement learning
- probability distribution
- maximum likelihood
- generative model
- machine learning algorithms
- loss function
- random variables
- color images
- image intensity
- real time