AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations

Bohan Zhou, Haoqi Yuan, Yuhui Fu, Zongqing Lu

AAAI 2026 · Reinforcement learning › Visual and representation RL · approach: Dexterous manipulation transfer · 26 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 the simulation alignment stage with approaching, lifting and bonus rewards (ablation)BiDexHD-IPPO teacher · TACO, Trainm2 tracking rate (%): 17.52 -> 78.18Improved
use functional grasping center instead of geometric center (ablation)BiDexHD-IPPO teacher · TACO, Trainm2 tracking rate (%): 66.39 -> 78.18Improved
use functional grasping center instead of geometric center (ablation)BiDexHD-IPPO teacher · TACO, Test Newm2 tracking rate (%): 22.63 vs 21.34No clear effect
add success bonus reward (ablation)BiDexHD-IPPO teacher · TACO, Trainm2 tracking rate (%): 66.65 -> 78.18Improved
add success bonus reward (ablation)BiDexHD-IPPO teacher · TACO, Test Newm2 tracking rate (%): 17.52 -> 21.34Mixed
use independent PPO instead of centralized PPO (ablation)BiDexHD teacher · TACO, Trainm2 tracking rate (%): 53.88 -> 78.18Improved
distill IPPO teachers with DAgger into a vision policyBiDexHD-IPPO · TACO, Test Newm2 tracking rate (%): 21.34 -> 53.71Improved
distill IPPO teachers with DAgger into a vision policyBiDexHD-IPPO · TACO, Trainm2 tracking rate (%): 78.18 -> 74.59Hurt
use DAgger from RL teachers instead of behavior cloning from retargeted demonstrationsvision-based student · TACO, all splitsm2 tracking rate (%): 00.00 -> 74.59 (Train)Improved
add K future object positions as student input (ablation)BiDexHD-IPPO+DAgger · TACO, Trainm2 tracking rate (%): K=0: 72.09, K=5: 74.59No clear effect
add K=5 future object positions as student input (ablation)BiDexHD-IPPO+DAgger · TACO, unseen tasksm2 tracking rate (%): average 3.1% gain over K=0Improved

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