Papers
arxiv:2511.13035

One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow

Published on Nov 17, 2025
Authors:
,
,
,
,
,
,

Abstract

A novel one-step generative policy for offline reinforcement learning reformulates MeanFlow to enable direct noise-to-action generation while maintaining multimodal action distribution modeling and single-stage training efficiency.

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable direct noise-to-action generation by integrating the velocity field and noise-to-action transformation into a single policy network-eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective residual formulation that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings. Code is available at https://github.com/HiccupRL/MeanFlowQL.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2511.13035
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2511.13035 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2511.13035 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2511.13035 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.