AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning

Yuto Shibata, Kashu Yamazaki, Lalit Jayanti, Yoshimitsu Aoki, Mariko Isogawa, Katerina Fragkiadaki

CVPR 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
joint MARL training instead of sequential training with a frozen recipient (ablation)AssistMimic · Inter-X specialistSuccess rate (%): 62.4 -> 74.9Improved
initialize policies from single-person motion prior (ablation)AssistMimic · Inter-X specialistSuccess rate (%): 0.0 -> 74.9Improved
initialize policies from single-person motion prior (ablation)AssistMimic · HHI-Assist specialistSuccess rate (%): 19.1 -> 85.8Improved
add dynamic reference retargeting (ablation)AssistMimic · Inter-X specialistSuccess rate (%): 83.4 -> 74.9Hurt
add dynamic reference retargeting (ablation)AssistMimic · HHI-Assist specialistSuccess rate (%), seen dynamics: 85.4 -> 85.8No clear effect
add dynamic reference retargeting (ablation)AssistMimic · HHI-Assist specialist (unseen dynamics)Success rate (%): 49.1 -> 67.8 (mass x1.5); 62.9 -> 73.2 (hip torque x0.5)Improved
add contact-promoting reward (ablation)AssistMimic · HHI-Assist specialistSuccess rate (%), seen dynamics: 97.7 -> 85.8Hurt
add contact-promoting reward (ablation)AssistMimic · HHI-Assist specialist (unseen dynamics)Success rate (%): 56.4 -> 67.8 (mass x1.5); 27.7 -> 73.2 (hip torque x0.5)Improved
add contact-promoting reward (ablation)AssistMimic · Inter-X specialistSuccess rate (%): seen 81.6 -> 74.9; mass x1.2 66.3 -> 57.9; Kp/Kd x0.5 77.1 -> 72.8Mixed
distill specialists into a generalist with DAgger (ablation)AssistMimic generalist · Inter-X generalist (30 clips)Success rate (%): 77.3 -> 94.7Improved

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