AI Paper Atlas

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

RFS: Reinforcement learning with Residual flow steering for dexterous manipulation

Entong Su, Tyler Westenbroek, Anusha Nagabandi, Abhishek Gupta

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 residual action steering to latent-noise steering (ablation)DSRL · Simulated tasks averagesuccess rate: 0.483 -> 0.861Improved
add residual action steering to latent-noise steering (ablation)DSRL · Simulated stackingsuccess rate: 0.135 -> 0.951Improved
add latent-noise steering to residual RL (ablation)ResiP · Simulated tasks averagesuccess rate: 0.433 -> 0.861Improved
add latent-noise steering to residual RL (ablation)Policy Decorator · Simulated tasks averagesuccess rate: 0.286 -> 0.861Improved
restrict RL to initial noise and residual instead of full denoising trajectoryReinFlow · Simulated tasks averagesuccess rate: 0.409 -> 0.861Improved
RL fine-tune the flow-matching base policy with RFSFlow Matching base policy · Simulated tasks averagesuccess rate: 0.250 -> 0.861Improved
add RFS fine-tuningFlow Matching base policy · Simulated pouringsuccess rate: 0.15 -> 0.873Improved
condition critic on executed action a_b+a_r instead of residual-only or concatenated actions (ablation)offline RFS · Real-world grasping and pick-and-placesuccess rateImproved
use offline RL fine-tuning instead of co-trainingdistilled sim policy · Real-world unseen objectssuccess rateImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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