We propose Drifting Field Policy (DFP), a non-ODE one-step generative policy built on the drifting model paradigm. We frame the policy update as a reverse-KL Wasserstein-2 gradient flow toward a soft target policy, so that each DFP update corresponds to a gradient step in probability space. By construction, this gradient is decomposed into an ascent toward higher action-value regions and a score matching with the anchor policy as a trust region. We further derive a simple, tractable surrogate of the otherwise intractable update loss, akin to behavior cloning on top-K critic-selected actions. We find empirically that this mechanism uniquely benefits the drifting backbone owing to its non-ODE parameterization. With one-step inference, DFP achieves state-of-the-art performance on several manipulation tasks across Robomimic and OGBench, outperforming ODE-based policies.
@article{arxiv.2605.07727,
title = {Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow},
author = {Juil Koo and Mingue Park and Jiwon Choi and Yunhong Min and Minhyuk Sung},
journal= {arXiv preprint arXiv:2605.07727},
year = {2026}
}