Showing cs.ROShow all
2 papers · 1 filter
cs.RO2026
ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning
Shaoyin Luo, Song Wang, Shibo Xia +5
Human-in-the-loop reinforcement learning (HIL-RL) offers a promising route to efficient training of robotic manipulation policies by combining autonomous learning with human demons…
cs.RO2026
Self-Curriculum Model-based Reinforcement Learning for Shape Control of Deformable Linear Objects
Zhaowei Liang, Song Wang, Zhao Jin +2
Precise shape control of Deformable Linear Objects (DLOs) is crucial in robotic applications such as industrial and medical fields. However, existing methods face challenges in han…