一作IROS 2026Poster· Guiding Long-Horizon Reinforcement Learning
HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning
Jingyi Liu · Zhaohong Mai · ShunSen He · Hang Ren · Chao Wang · Shunbo Zhou · XiaoDong Wu · Heng Zhang
强化学习与后训练检索与知识社会与人本Reinforcement LearningImitation LearningHuman Factors and Human-in-the-LoopOpenReview