Fisher-Rao Gradient Flows of Linear Programs and State-Action Natural Policy Gradients

arXiv:2403.19448v3 Announce Type: replace-cross Abstract: Kakade's natural policy gradient method has been studied extensively in recent years, showing linear convergence with and without regularization. We study another natural gradient method based on the Fisher information matrix of the state-action distributions which has received little attention from the theoretical side. Here, the state-action distributions follow the Fisher-Rao gradient flow inside the state-action polytope with respect to a linear potential. Therefore, we study Fisher-Rao gradient flows of linear programs more generally and show linear convergence with a rate that depends on the geometry of the linear program. Equivalently, this yields an estimate on the error induced by entropic regularization of the linear program which improves existing results. We extend these results and show sublinear convergence for perturbed Fisher-Rao gradient flows and natural gradient flows up to an approximation error. In particular, these general results cover the case of state-action natural policy gradients.

Related

• Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning
• Global linear convergence of entropy-regularized softmax policy gradient beyond tabular MDPs
• A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance

Source: arXiv cs.LG | 2026-09-11