Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation

ICLR 2026 Conference Submission13298 Authors

Keywords: Reinforcement learning, Generative policy

TL;DR: We introduce the mean flow policy, a new RL policy that, along with a novel instantaneous velocity constraint, achieves state-of-the-art performance and the fastest training and inference speed.

Abstract: Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling process, they still face a trade-off between expressiveness and computational burden, which is typically controlled by the number of flow steps. In this work, we propose mean flow policy (MFP), a new generative policy function that models the mean velocity field to achieve the fastest one-step action generation. To ensure its high expressiveness, an instantaneous velocity constraint (IVC) is introduced on the mean velocity field during training. We theoretically prove that this design explicitly serves as a crucial boundary condition, thereby improving learning accuracy and enhancing policy expressiveness. Empirically, our MFP achieves state-of-the-art success rates across several challenging robotic manipulation tasks from Robomimic and OGBench. It also delivers substantial improvements in training and inference speed over existing flow-based policy baselines.

Primary Area: reinforcement learning

Submission Number: 13298