AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement Learning

Patrick Yin, Tyler Westenbroek, Zhengyu Zhang, Ignacio Dagnino, Eeshani Shilamkar, Numfor Mbiziwo-Tiapo, Simran Bagaria, Xinlei Liu, Galen Mullins, Andrey Kolobov, Abhishek Gupta

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 12 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 OmniReset distilled RGB policy instead of real-only BC (100 demos)real-world policy · Peg Insertion realsuccess rate: 2.44% -> 85.37%Improved
use OmniReset distilled RGB policy instead of real-only BC (100 demos)real-world policy · Leg Twisting realsuccess rate: 1.82% -> 56.36%Improved
use OmniReset distilled RGB policy instead of real-only BC (100 demos)real-world policy · Drawer Insertion realsuccess rate: 1.92% -> 15.38%Improved
distill state-based RL expert into RGB policyOmniReset · Peg Insertion simsuccess rate: 94.97% -> 55.45%Hurt
distill state-based RL expert into RGB policyOmniReset · Leg Twisting simsuccess rate: 93.94% -> 43.69%Hurt
distill state-based RL expert into RGB policyOmniReset · Drawer Insertion simsuccess rate: 89.60% -> 84.00%Hurt
increase number of parallel environments (ablation)OmniReset PPO · Leg Twisting Hardsuccess rate from Reaching resetsImproved
broaden grasp sampling range (narrow to broad) (ablation)OmniReset · Leg Twistingsample efficiency and success rateImproved
use OmniReset instead of Demo Curriculum, BC-PPO, DeepMimicRL training · Hard task variantssuccess rateImproved
scale distillation data from 10K to 80K trajectories (ablation)distilled RGB policy · real-world transfersuccess rateImproved
freeze visual encoder instead of end-to-end training (ablation)distilled RGB policy · distillationsuccess rateHurt
replace OSC with joint-space PD control (ablation)RL and distillation · controller designsuccess rateHurt

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