Convergence of Flow-Policy Gradient Learning for Linear Quadratic Regulator Problems
Abstract
Flow -learning has recently been introduced to integrate learning from expert demonstrations into an actor-critic structure. Central to this innovation is the ``the one-step policy'' network, which is optimized through a -function that is regularized with the behavioral cloning from expert trajectories, allowing learning more expressive policies using flow-based generative models. In this paper, we studied the convergence property and stabilizablity of the one-step policy during learning for linear quadratic problems under the offline settings. Our theoretical results are based on a new formulation of the one-step policy loss based on the average expected cost, and regularized with the behavioral cloning loss. Such a formulation allows us to tap into existing strong theoretical results from the policy gradient theorem to study the convergence properties of the one-step policy. We verify our theoretical finding with simulation results on a linearized inverted pendulum.
Cite
@article{arxiv.2511.11131,
title = {Convergence of Flow-Policy Gradient Learning for Linear Quadratic Regulator Problems},
author = {Farnaz Adib Yaghmaie and Arunava Naha},
journal= {arXiv preprint arXiv:2511.11131},
year = {2025}
}
Comments
Submitted to L4DC