AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable Physics

Junyi Cao, Yian Wang, Ziyan Xiong, Chunru Lin, Zhehuan Chen, Chuang Gan

ICML 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 0 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 Coefficient mode instead of Candidate mode for VLM grasp proposal (ablation)CMA-ES · DLO-Lab Unknottingmax episodic return: 57.21 -> 3.06Hurt
use Marker mode instead of Candidate mode for VLM grasp proposal (ablation)CMA-ES · DLO-Lab Wrappingmax episodic return: 162.68 -> 136.39Hurt
use Coefficient mode instead of Candidate mode for VLM grasp proposal (ablation)CMA-ES · DLO-Lab Wrappingmax episodic return: 162.68 -> 144.78Hurt
use Coefficient mode instead of Candidate mode for VLM grasp proposal (ablation)CMA-ES · DLO-Lab Liftingmax episodic return: 335.59 -> 330.57Hurt
add dynamic plan update to VLM task decomposition (ablation)DLO agent with CMA-ES · Wiring-ringtask completion (qualitative)Improved
add dynamic plan update to VLM task decomposition (ablation)DLO agent with CMA-ES · Letter Arttask completion (qualitative)No clear effect
use sample-based CMA-ES trajectory optimization instead of gradient descenttrajectory optimization · DLO-Lab Unknottingmax episodic return: 3.44 -> 57.21Improved
use first-order model-based RL (SAPO) instead of PPO/SACRL · DLO-Lab Unknottingmax episodic return: 3 -> 46Improved
use CMA-ES instead of SAPOFO-MBRL · DLO-Lab success rate averagesuccess rate (%): 35.0% -> 86.6%Improved
use GD instead of CMA-ES on smooth taskstrajectory optimization · DLO-Lab Separationmax episodic return: 84.86 -> 115.52Mixed

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