On-Policy Data-Driven Linear Quadratic Regulator via Model Reference Adaptive Reinforcement Learning.
Marco BorghesiAlessandro BossoGiuseppe NotarstefanoPublished in: CDC (2023)
Keyphrases
- linear quadratic
- data driven
- optimal control
- model reference adaptive
- reinforcement learning
- optimal policy
- policy search
- closed loop
- dynamical systems
- action selection
- vector valued
- dynamic programming
- state space
- reward function
- markov decision processes
- gaussian model
- learning problems
- control strategy
- machine learning
- learning theory
- maximum likelihood
- supervised learning
- image segmentation