Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cheng, Xiaoyuan, Wang, Haoyu, Yuan, Wenxuan, Wang, Ziyan, Chen, Zonghao, Zeng, Li, Sun, Zhuo
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.17919
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913090275115008
author Cheng, Xiaoyuan
Wang, Haoyu
Yuan, Wenxuan
Wang, Ziyan
Chen, Zonghao
Zeng, Li
Sun, Zhuo
author_facet Cheng, Xiaoyuan
Wang, Haoyu
Yuan, Wenxuan
Wang, Ziyan
Chen, Zonghao
Zeng, Li
Sun, Zhuo
contents Recent advances in flow-based offline reinforcement learning (RL) have achieved strong performance by parameterizing policies via flow matching. However, they still face critical trade-offs among expressiveness, optimality, and efficiency. In particular, existing flow policies interpret the $L_2$ regularization as an upper bound of the 2-Wasserstein distance ($W_2$), which can be problematic in offline settings. This issue stems from a fundamental geometric mismatch: the behavioral policy manifold is inherently anisotropic, whereas the $L_2$ (or upper bound of $W_2$) regularization is isotropic and density-insensitive, leading to systematically misaligned optimization directions. To address this, we revisit offline RL from a geometric perspective and show that policy refinement can be formulated as a local transport map: an initial flow policy augmented by a residual displacement. By analyzing the induced density transformation, we derive a local quadratic approximation of the KL-constrained objective governed by the Fisher information matrix, enabling a tractable anisotropic optimization formulation. By leveraging the score function embedded in the flow velocity, we obtain a corresponding quadratic constraint for efficient optimization. Our results reveal that the optimality gap in prior methods arises from their isotropic approximation. In contrast, our framework achieves a controllable approximation error within a provable neighborhood of the optimal solution. Extensive experiments demonstrate state-of-the-art performance across diverse offline RL benchmarks. See project page: https://github.com/ARC0127/Fisher-Decorator.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17919
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Fisher Decorator: Refining Flow Policy via a Local Transport Map
Cheng, Xiaoyuan
Wang, Haoyu
Yuan, Wenxuan
Wang, Ziyan
Chen, Zonghao
Zeng, Li
Sun, Zhuo
Machine Learning
Robotics
Recent advances in flow-based offline reinforcement learning (RL) have achieved strong performance by parameterizing policies via flow matching. However, they still face critical trade-offs among expressiveness, optimality, and efficiency. In particular, existing flow policies interpret the $L_2$ regularization as an upper bound of the 2-Wasserstein distance ($W_2$), which can be problematic in offline settings. This issue stems from a fundamental geometric mismatch: the behavioral policy manifold is inherently anisotropic, whereas the $L_2$ (or upper bound of $W_2$) regularization is isotropic and density-insensitive, leading to systematically misaligned optimization directions. To address this, we revisit offline RL from a geometric perspective and show that policy refinement can be formulated as a local transport map: an initial flow policy augmented by a residual displacement. By analyzing the induced density transformation, we derive a local quadratic approximation of the KL-constrained objective governed by the Fisher information matrix, enabling a tractable anisotropic optimization formulation. By leveraging the score function embedded in the flow velocity, we obtain a corresponding quadratic constraint for efficient optimization. Our results reveal that the optimality gap in prior methods arises from their isotropic approximation. In contrast, our framework achieves a controllable approximation error within a provable neighborhood of the optimal solution. Extensive experiments demonstrate state-of-the-art performance across diverse offline RL benchmarks. See project page: https://github.com/ARC0127/Fisher-Decorator.
title Fisher Decorator: Refining Flow Policy via a Local Transport Map
topic Machine Learning
Robotics
url https://arxiv.org/abs/2604.17919