Log In Sign Up

Towards a Dimension-Free Understanding of Adaptive Linear Control

by   Juan C. Perdomo, et al.

We study the problem of adaptive control of the linear quadratic regulator for systems in very high, or even infinite dimension. We demonstrate that while sublinear regret requires finite dimensional inputs, the ambient state dimension of the system need not be bounded in order to perform online control. We provide the first regret bounds for LQR which hold for infinite dimensional systems, replacing dependence on ambient dimension with more natural notions of problem complexity. Our guarantees arise from a novel perturbation bound for certainty equivalence which scales with the prediction error in estimating the system parameters, without requiring consistent parameter recovery in more stringent measures like the operator norm. When specialized to finite dimensional settings, our bounds recover near optimal dimension and time horizon dependence.


page 1

page 2

page 3

page 4


Naive Exploration is Optimal for Online LQR

We consider the problem of online adaptive control of the linear quadrat...

Regret Bounds for Adaptive Nonlinear Control

We study the problem of adaptively controlling a known discrete-time non...

Efficient Reinforcement Learning for High Dimensional Linear Quadratic Systems

We study the problem of adaptive control of a high dimensional linear qu...

Robust Online Control with Model Misspecification

We study online control of an unknown nonlinear dynamical system that is...

Information Theoretic Regret Bounds for Online Nonlinear Control

This work studies the problem of sequential control in an unknown, nonli...

Online Control of Unknown Time-Varying Dynamical Systems

We study online control of time-varying linear systems with unknown dyna...

Learning to Control Linear Systems can be Hard

In this paper, we study the statistical difficulty of learning to contro...