Score: 1

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

Published: November 17, 2025 | arXiv ID: 2511.13035v1

By: Zeyuan Wang , Da Li , Yulin Chen and more

Potential Business Impact:

Teaches robots to learn from past actions.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

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.

Country of Origin
🇨🇳 China

Repos / Data Links

Page Count
23 pages

Category
Computer Science:
Machine Learning (CS)