One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow
This addresses the challenge of expressive and efficient policy learning in offline RL, offering improvements over existing flow-based methods by enabling single-stage training with Q-learning.
The paper tackles the problem of capturing complex, multimodal action distributions in offline reinforcement learning by introducing a one-step generative policy that reformulates MeanFlow for direct noise-to-action mapping, achieving strong performance on 73 tasks across OGBench and D4RL benchmarks.
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.