Boosting Offline Reinforcement Learning with Action Preference QueryXiaochen Zhao, Shenzhi Wang, Matthieu Gaetan Lin, Shiji Song, Gao HuangLast updated on Dec 14, 2023PDF Cite ArxivXiaochen ZhaoPhD Candidate of 3D VisionMy research interests include digital human, 3D GAN, AIGC and 3D reconstruction.