AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

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

Zeyuan Wang, Da Li, Yulin Chen, Ye Shi, Liang Bai, Tianyuan Yu, Yanwei Fu

AAAI 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Regularized scalable deep value learning · 5 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use residual reformulation g = a_t - u instead of naive MeanFlow noise-to-velocity-to-action (ablation)one-step policy with Q-learning · antsoccer-arena-singletasksuccess rateImproved
increase candidate size K in value-guided rejection sampling from 1 to 5 (ablation)one-step policy · OGBench tasks (humanoidmaze-large, antmaze-large-play, visual puzzle-3x3)success rateImproved
increase candidate size K to 20 (ablation)one-step policy · OGBench taskssuccess rateHurt
vary behaviour-cloning coefficient alpha (even with adaptive tuning) (ablation)one-step policy · Puzzle3x3, humanoidmaze-large, antmaze-medium-playsuccess rateMixed
one-step MeanFlow policy versus FQL on puzzle-3x3one-step policy · OGBench puzzle-3x3-singletasksuccess rate (%): 30 -> 66Improved
one-step MeanFlow policy versus FQL on cube-double and antmaze-giant (offline)one-step policy · OGBench cube-double / antmaze-giant singletasksuccess rate (%): 29 -> 3 (cube-double); 9 -> 0 (antmaze-giant)Hurt
online fine-tuning after offline trainingone-step policy · antmaze-giant-navigate, cube-double-playsuccess rate (%): 0 -> 82 (antmaze-giant); 3 -> 95 (cube-double-play)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy