Sample Complexity of Linear Quadratic Regulator Without Initial Stability
Optimization and Control
2025-10-07 v3 Machine Learning
Systems and Control
Systems and Control
Abstract
Inspired by REINFORCE, we introduce a novel receding-horizon algorithm for the Linear Quadratic Regulator (LQR) problem with unknown dynamics. Unlike prior methods, our algorithm avoids reliance on two-point gradient estimates while maintaining the same order of sample complexity. Furthermore, it eliminates the restrictive requirement of starting with a stable initial policy, broadening its applicability. Beyond these improvements, we introduce a refined analysis of error propagation through the contraction of the Riccati operator under the Riemannian distance. This refinement leads to a better sample complexity and ensures improved convergence guarantees.
Cite
@article{arxiv.2502.14210,
title = {Sample Complexity of Linear Quadratic Regulator Without Initial Stability},
author = {Amirreza Neshaei Moghaddam and Alex Olshevsky and Bahman Gharesifard},
journal= {arXiv preprint arXiv:2502.14210},
year = {2025}
}