AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation

Qianzhong Chen, Justin Yu, Mac Schwager, Pieter Abbeel, Fred Shentu, Philipp Wu

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer

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
stage-aware progress labels from subtask annotations (SARM) vs ReWiNDreward model · T-shirt rollout classificationrho: 0.50 -> 0.94Improved
add rewind augmentation (ablation)SARM · T-shirt rolloutsrho: 0.67 -> 0.94Improved
add rewind augmentation (ablation)SARM · T-shirt demo validationMSE: 0.008 -> 0.009No clear effect
train on both dense and sparse annotations instead of dense only (ablation)SARM · T-shirt rolloutsrho: 0.11 -> 0.94Improved
train on both annotation schemes instead of sparse only (ablation)SARM · T-shirt rolloutsrho: 0.78 -> 0.94Improved
perturb frame brightness by up to 0.3 (ablation)SARM · T-shirt rolloutsrho: 0.94 -> 0.78Hurt
filter demonstrations to under 2 minutes (BC-2min vs BC-All) (ablation)Pi0 BC · T-shirt medium task, 40Ksuccess: 1/12 -> 7/12Improved
duration filtering only, on the hard task (ablation)Pi0 BC · T-shirt hard task, 40Ksuccess: 0/12 -> 0/12No clear effect
apply RA-BC with SARM instead of BC-2minPi0 · T-shirt hard task, 40Ksuccess: 0/12 -> 8/12Improved
use SARM rather than ReWiND reward model in RA-BC (ablation)RA-BC · T-shirt medium task, 40Ksuccess: 6/12 -> 10/12Improved
RA-BC with ReWiND reward model instead of plain BC-2min (ablation)Pi0 · T-shirt medium task, 40Ksuccess: 7/12 -> 6/12No clear effect
increase reward model from 4 to 8 layers (ablation)SARM · T-shirt rolloutsrho: 0.72 -> 0.94Improved

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