AI Paper Atlas

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

SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling

Yixian Zhang, Shu'ang Yu, Tonghe Zhang, Mo Guang, Haojia Hui, Kaiwen Long, Yu Wang, Chao Yu, Wenbo Ding

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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
reparameterize velocity network with GRU-style gate (Flow-G) or Transformer-decoded velocity (Flow-T) instead of plain MLP velocity (ablation)SAC Flow · Gradient norm during SAC traininggradient stability: max variation of 0.29Improved
apply SAC directly to a flow policy without velocity reparameterization (ablation)SAC Flow naive baseline · MuJoCo from scratch and OGBench offline-to-onlinereturn / success rateHurt
increase flow sampling steps K from 4 to 7 and 10 (ablation)SAC Flow-T and SAC Flow-G · ablation on sampling stepsperformanceNo clear effect
use SAC Flow instead of FlowRL for from-scratch trainingflow-based policy · MuJoCo from scratchreturn: up to 130% improvementImproved
use SAC Flow-T vs prior methods in offline-to-onlineOGBench cube-triple and cube-quadruple · OGBench offline-to-onlinesuccess rate: up to 60% improvementImproved
use SAC Flow with strongly regularized training (large beta)SAC Flow-G and Flow-T · Robomimic offline-to-onlinesuccess rateNo clear effect
use SAC Flow instead of DIME on HumanoidSAC Flow · MuJoCo Humanoid from scratchreturnNo clear effect

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