arXiv Machine Learning September 3, 2026 By Amirreza Neshaei Moghaddam, Alex Olshevsky, Bahman Gharesifard

Sample Complexity of Linear Quadratic Regulator Without Initial Stability

Read the original on arXiv Machine Learning →

The paper proposes a new receding‑horizon algorithm for the Linear Quadratic Regulator (LQR) with unknown dynamics, inspired by REINFORCE. It removes the need for two‑point gradient estimates and does not require a stable initial policy, while maintaining the same order of sample complexity. A refined analysis of error propagation via the Riccati operator’s contraction under Riemannian distance yields improved sample complexity and convergence guarantees.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jun 24

Hessian-augmented Supervised Learning for Hamilton-Jacobi-Bellman PDEs

arXiv:2606. 23827v1 Announce Type: cross Abstract: A data-driven method is developed for approximating value functions in deterministic optimal control problems with nonlinear control-affine dynamics.

By Mat\'ias G\'omez-Aedo, Behzad Azmi, Yuyang Huang, Dante Kalise, Karl Kunisch

arXiv Machine Learning

Jul 23

Any-Time Regret-Guaranteed Algorithm for Control of Linear Quadratic Systems

arXiv:2406. 07746v4 Announce Type: replace-cross Abstract: We propose a computationally efficient algorithm that achieves anytime regret of order $\mathcal{O}(\sqrt{t})$, with explicit dependence on the system dimensions and on the solution of the Discrete Algebraic Riccati Equation (DARE).

By Jafar Abbaszadeh Chekan, Cedric Langbort

arXiv Machine Learning

Jul 3

A Unified Lyapunov-IQC Framework for Uniform Stability of Smooth Quadratic First-Order Accelerated Optimizers

arXiv:2605. 08488v2 Announce Type: replace-cross Abstract: We develop a unified Lyapunov-integral quadratic constraint (IQC) framework for establishing uniform stability of first-order accelerated optimization algorithms in the $\beta$-smooth and $\gamma$-strongly convex regime.

By Don Li, Dacian Daescu

arXiv AI

Jul 3

Horizon-Uniform Sensitivity Certificates for Finite-Horizon Pontryagin Systems

arXiv:2606. 17762v2 Announce Type: replace-cross Abstract: Finite-horizon optimal-control computations repeatedly solve two-point Pontryagin boundary value problems whose conditioning can deteriorate as the horizon grows.

By Pyuyi Chufeng Huang, Zikang Song, Xingshu Chen

arXiv AI

Jul 10

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition

arXiv:2605. 14982v2 Announce Type: replace-cross Abstract: We address the discounted reward setting in reinforcement learning (RL).

By Sanjeev Manivannan, Shuban V

reinforcement-learning

arXiv Machine Learning

Jun 24

Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum

arXiv:2406. 13041v3 Announce Type: replace Abstract: Lower-bound analyses for nonconvex strongly-concave minimax optimization problems have shown that stochastic first-order algorithms require at least $\mathcal{O}(\varepsilon^{-4})$ sample complexity to find an $\varepsilon$-stationary point.

By Haoyuan Cai, Sulaiman A. Alghunaim, Ali H. Sayed

safety

One email a morning, machine-written

Related stories

Hessian-augmented Supervised Learning for Hamilton-Jacobi-Bellman PDEs

Any-Time Regret-Guaranteed Algorithm for Control of Linear Quadratic Systems

A Unified Lyapunov-IQC Framework for Uniform Stability of Smooth Quadratic First-Order Accelerated Optimizers

Horizon-Uniform Sensitivity Certificates for Finite-Horizon Pontryagin Systems

Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition

Accelerated Stochastic Min-Max Optimization Based on Bias-corrected Momentum