Avoiding $\mathbf{exp(R_{max})}$ scaling in RLHF through Preference-based Exploration
机构 * Department of Electrical & Computer Engineering(电气与计算机工程系) ; Boston University(波士顿大学) ; Department of Computer Science(计算机科学系) ; Cornell University(康奈尔大学) ; Faculty of Computing & Data Sciences(计算与数据科学学院)
专题命中 偏好对齐 :RLHF(title,abstract);alignment(abstract);分类 cs.AI、cs.LG