Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics.
Feicheng WangLucas JansonPublished in: CoRR (2022)
Keyphrases
- linear quadratic
- lower bound
- dynamical systems
- closed loop
- optimal control
- upper bound
- vector valued
- worst case
- matching algorithm
- gaussian model
- state space
- objective function
- optimal solution
- online algorithms
- medical images
- regret bounds
- maximum likelihood
- template matching
- machine learning
- dynamic programming
- special case
- image segmentation