AI Paper Atlas

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

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

Guojian Zhan, Letian Tao, Pengcheng Wang, Yixiao Wang, Yuxin Chen, Yiheng Li, Hongyang Li, Masayoshi Tomizuka, Shengbo Eben Li

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 4 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
add instantaneous velocity constraint (lambda 0 -> 1.0) (ablation)MVP · Cube-triple-task4success rate: 0.30 -> 0.52Improved
add instantaneous velocity constraint (lambda 0 -> 1.0) (ablation)MVP · Cube-triple-task3success rate: 0.65 -> 0.71Improved
replace multi-step flow with mean-velocity one-step policy (ablation)QC-style chunked best-of-N policy · Cube-triple-task4success rate: 0.01 -> 0.52Improved
replace standard one-step flow with mean velocity policy (ablation)FQL-Onestep · Cube-triple-task3success rate: 0.00 -> 0.71Improved
use one-step mean velocity generation instead of 10-step flowBFN/QC · Inference timems: 117.3 -> 10.93 msImproved
use mean velocity policy instead of FQL distillationFQL · Online training speediter/s: 108.5 -> 153.6 iter/sImproved
use mean velocity policy vs QC on easier tasksQC · Robomimic-cansuccess rate: 0.94 -> 0.92Hurt
use MVP vs QC on hardest taskQC · Cube-triple-task4success rate: 0.46 -> 0.52Improved

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