PreprintarXiv licencearXiv
Policy Iteration for Domain Randomized Linear Quadratic Systems
Abstract
In this work, we study policy optimization under domain randomization for linear quadratic control, focusing on learning a single state-feedback controller that minimizes the average cost across systems with uncertain dynamics. We propose a policy iteration algorithm with a step-size rule that preserves stability across all sampled systems at each iteration. We show that the method yields monotonic improvement of the sample-average objective and that a stabilizing step size always exists. Under standard smoothness assumptions, the iterates converge subsequentially to stationary points, and under a gradient-dominance condition, we obtain a global linear convergence rate.
Related
- The Effect of Quadrature on the Convergence of Policy Iteration for Hamilton-Jacobi-Bellman Equations
- Policy iteration for Hamilton-Jacobi-Isaacs equations with control constraints and comparison with Hamilton-Jacobi-Bellman equations
- Continuous Policy and Value Iteration for Stochastic Control Problems with Inhomogeneous Synchronous Coupling
- Policy Iteration Is Not Strongly Polynomial for Deterministic Markov Decision Processes: The Price of Algorithmic Anarchy
- A Newton--Kleinman Iteration for Infinite-Dimensional Linear-Quadratic Optimal Control
BibTeX
@misc{pasdar2026policy,
title = {{Policy Iteration for Domain Randomized Linear Quadratic Systems}},
author = {Abbas Pasdar and Farnaz Adib Yaghmaie},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.04794},
eprint = {2609.04794},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.04794},
}
RIS
TY - UNPB
TI - Policy Iteration for Domain Randomized Linear Quadratic Systems
AU - Abbas Pasdar
AU - Farnaz Adib Yaghmaie
PY - 2026
DA - 2026/09/09
PB - arXiv
DO - 10.48550/arxiv.2609.04794
UR - https://arxiv.org/abs/2609.04794
AB - In this work, we study policy optimization under domain randomization for linear quadratic control, focusing on learning a single state-feedback controller that minimizes the average cost across systems with uncertain dynamics. We propose a policy iteration algorithm with a step-size rule that preserves stability across all sampled systems at each iteration. We show that the method yields monotonic improvement of the sample-average objective and that a stabilizing step size always exists. Under standard smoothness assumptions, the iterates converge subsequentially to stationary points, and under a gradient-dominance condition, we obtain a global linear convergence rate.
ER -