作者位次 #3/3NeurIPS 2026Poster
Optimistic Q-value Adaptation for Offline-to-Online Reinforcement Learning
Hao Wu · Shunhao Zhang · Shuai Lü
强化学习与后训练OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Hao Wu · Shunhao Zhang · Shuai Lü
Wensi Fang · Xiaodan Zhang · Xiaoyu Lian · Qiang Li · Shuai Lü
Unsupervised cross-domain image retrieval aims to retrieve semantically consistent images across domains with significant domain gaps, which poses substantial challenges under the absence of annotations in both domains. Existing approaches primarily rely on internally derived supervision signals...
Songlin Li · Wei Xiao · Hao Wu · Xiaodan Zhang · Daolong An · Shuai Lü
Zeyu Zhang · Chun Shen · Qiang Ma · Meng Kang · Shuai Lü