Learning Controllers for Unstable Linear Quadratic Regulators from a Single Trajectory

06/19/2020
by   Lenart Treven, et al.
0

We present the first approach for learning – from a single trajectory – a linear quadratic regulator (LQR), even for unstable systems, without knowledge of the system dynamics and without requiring an initial stabilizing controller. Our central contribution is an efficient algorithm – eXploration – that quickly identifies a stabilizing controller. Our approach utilizes robust System Level Synthesis (SLS), and we prove that it succeeds in a constant number of iterations. Our approach can be used to initialize existing algorithms that require a stabilizing controller as input. When used in this way, it yields a method for learning LQRs from a single trajectory and even for unstable systems, while suffering at most 𝒪(√(T)) regret.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/17/2019

Learning Linear-Quadratic Regulators Efficiently with only √(T) Regret

We present the first computationally-efficient algorithm with O(√(T)) r...
10/31/2021

Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees

We study the adaptive control of an unknown linear system with a quadrat...
07/23/2020

Explore More and Improve Regret in Linear Quadratic Regulators

Stabilizing the unknown dynamics of a control system and minimizing regr...
11/23/2015

Learning Simple Algorithms from Examples

We present an approach for learning simple algorithms such as copying, m...
07/13/2020

Efficient Optimistic Exploration in Linear-Quadratic Regulators via Lagrangian Relaxation

We study the exploration-exploitation dilemma in the linear quadratic re...
09/21/2019

Efficient Learning of Distributed Linear-Quadratic Controllers

In this work, we propose a robust approach to design distributed control...
09/26/2018

Safely Learning to Control the Constrained Linear Quadratic Regulator

We study the constrained linear quadratic regulator with unknown dynamic...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.