{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:19:29Z","timestamp":1773803969777,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"31","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>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.\nWhile 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.\nTo 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\u2014eliminating 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.\nExtensive 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.<\/jats:p>","DOI":"10.1609\/aaai.v40i31.39885","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:10:48Z","timestamp":1773799848000},"page":"26751-26759","source":"Crossref","is-referenced-by-count":0,"title":["One-Step Generative Policies with Q-Learning: A Reformulation of MeanFlow"],"prefix":"10.1609","volume":"40","author":[{"given":"Zeyuan","family":"Wang","sequence":"first","affiliation":[]},{"given":"Da","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yulin","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ye","family":"Shi","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Tianyuan","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Yanwei","family":"Fu","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39885\/43846","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39885\/43846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:10:49Z","timestamp":1773799849000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"31","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i31.39885","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}