-
Logarithmic Regret for Online Control
We study optimal regret bounds for control in linear dynamical systems u...
09/11/2019 ∙ by Naman Agarwal, et al. ∙
0
∙
share
read it
-
Nonsmooth optimal value and policy functions for mechanical systems subject to unilateral constraints
State-of-the-art approaches to optimal control of contact-rich robot dyn...
10/18/2017 ∙ by Bora S. Banjanin, et al. ∙
0
∙
share
read it
-
The Power of Linear Controllers in LQR Control
The Linear Quadratic Regulator (LQR) framework considers the problem of ...
02/07/2020 ∙ by Gautam Goel, et al. ∙
0
∙
share
read it
-
Moreau-Yosida regularization for optimal control of fractional PDEs with state constraints: parabolic case
This paper considers optimal control of fractional parabolic PDEs with b...
04/20/2020 ∙ by Harbir Antil, et al. ∙
0
∙
share
read it
-
Optimal Control of a Differentially Flat 2D Spring-Loaded Inverted Pendulum Model
This paper considers the optimal control problem of an extended spring-l...
11/17/2019 ∙ by Hua Chen, et al. ∙
0
∙
share
read it
-
Distributed Online Linear Quadratic Control for Linear Time-invariant Systems
Classical linear quadratic (LQ) control centers around linear time-invar...
09/29/2020 ∙ by Ting-Jui Chang, et al. ∙
0
∙
share
read it
-
Adaptive scale-invariant online algorithms for learning linear models
We consider online learning with linear models, where the algorithm pred...
02/20/2019 ∙ by Michał Kempka, et al. ∙
0
∙
share
read it
Online Optimal Control with Affine Constraints
10/10/2020 ∙ by Yingying Li, et al. ∙
0
∙
share
This paper considers online optimal control with affine constraints on the states and actions under linear dynamics with random disturbances. We consider convex stage cost functions that change adversarially. Besides, we consider time-invariant and known system dynamics and constraints. To solve this problem, we propose Online Gradient Descent with Buffer Zone (OGD-BZ). Theoretically, we show that OGD-BZ can guarantee the system to satisfy all the constraints despite any realization of the disturbances under proper parameters. Further, we investigate the policy regret of OGD-BZ, which compares OGD-BZ's performance with the performance of the optimal linear policy in hindsight. We show that OGD-BZ can achieve Õ(√(T)) policy regret under proper parameters, where Õ(·) absorbs logarithmic terms of T.
READ FULL TEXT
Comments
There are no comments yet.