2 papers
cs.RO2026
Preference-Calibrated Human-in-the-Loop Reinforcement Learning for Robotic Manipulation
Zeyi Liu, Guangyao Liu, Yinuo Qu +6
Human-in-the-loop reinforcement learning (HIL-RL) improves sample efficiency in real-robot manipulation through online human intervention. However, successful trajectories may incl…
cs.RO2026
WorldSample: Closed-loop Real-robot RL with World Modelling
Yuquan Xue, Le Xu, Zeyi Liu +5
Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond t…