Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Moghaddam, Amirreza Neshaei, Olshevsky, Alex, Gharesifard, Bahman
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908409467502592
author Moghaddam, Amirreza Neshaei
Olshevsky, Alex
Gharesifard, Bahman
author_facet Moghaddam, Amirreza Neshaei
Olshevsky, Alex
Gharesifard, Bahman
contents We provide the first known algorithm that provably achieves $\varepsilon$-optimality within $\widetilde{\mathcal{O}}(1/\varepsilon)$ function evaluations for the discounted discrete-time LQR problem with unknown parameters, without relying on two-point gradient estimates. These estimates are known to be unrealistic in many settings, as they depend on using the exact same initialization, which is to be selected randomly, for two different policies. Our results substantially improve upon the existing literature outside the realm of two-point gradient estimates, which either leads to $\widetilde{\mathcal{O}}(1/\varepsilon^2)$ rates or heavily relies on stability assumptions.
format Preprint
id arxiv_https___arxiv_org_abs_2404_10851
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
Moghaddam, Amirreza Neshaei
Olshevsky, Alex
Gharesifard, Bahman
Systems and Control
Machine Learning
Optimization and Control
We provide the first known algorithm that provably achieves $\varepsilon$-optimality within $\widetilde{\mathcal{O}}(1/\varepsilon)$ function evaluations for the discounted discrete-time LQR problem with unknown parameters, without relying on two-point gradient estimates. These estimates are known to be unrealistic in many settings, as they depend on using the exact same initialization, which is to be selected randomly, for two different policies. Our results substantially improve upon the existing literature outside the realm of two-point gradient estimates, which either leads to $\widetilde{\mathcal{O}}(1/\varepsilon^2)$ rates or heavily relies on stability assumptions.
title Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens
topic Systems and Control
Machine Learning
Optimization and Control
url https://arxiv.org/abs/2404.10851