作者位次 #2/6ICLR 2026Poster· Reinforcement Learning / Online
Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
Dongxie Wen · Hanyan Yin · Xiao Zhang · Peng Zhao · Lijun Zhang · Zhewei Wei
强化学习与后训练OpenReview