[논문 리뷰] SURF: semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning

논문 정보

제목: SURF: semi-supervised reward learning with data augmentation for feedback-efficient preference-based reinforcement learning

저자: Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee.

학회: ICLR 2022

링크: https://arxiv.org/abs/2203.10050