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.
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.
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).
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.
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.
arXiv:2605. 14982v2 Announce Type: replace-cross Abstract: We address the discounted reward setting in reinforcement learning (RL).
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.
arXiv:2609. 21880v1 Announce Type: cross Abstract: We study the optimization of convex objectives with $(L,\kappa-1)$-H\"older-continuous gradients in $\ell_q$ over $R B_p^d$, $1<\kappa\le 2$.
arXiv:2302.07477v4 Announce Type: replace Abstract: We study the optimal sample complexity of tabular reinforcement learning for infinite-horizon discounted Markov decision processes. The unrestricte...
arXiv:2608. 07433v1 Announce Type: cross Abstract: Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space.
arXiv:2507. 19895v4 Announce Type: replace-cross Abstract: In this paper, we study the distributed linear quadratic problem with fixed communication topology (DFT-LQ) and the sparse feedback linear quadratic (SF-LQ) problem through a unified optimization framework.
arXiv:2608.30431v1 Announce Type: cross Abstract: By focusing on algorithmic stability as a means of establishing out-of-sample bounds, we provide a system-theoretic interpretation of generalization...
arXiv:2510. 01943v3 Announce Type: replace-cross Abstract: Quasar-convex functions form a broad nonconvex class with applications to linear dynamical systems, generalized linear models, and Riemannian optimization, among others.