作者位次 #2/2ICLR 2026Poster· Reinforcement Learning / Batch/Offline
One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning
Xuan Thanh Nguyen · Chang Yoo
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。
Xuan Thanh Nguyen · Chang Yoo
Trung X. Pham · Kang Zhang · Ji Woo Hong · Chang Yoo
Seong Jin Cho · Gwangsu Kim · Junghyun Lee · Hee Suk Yoon · Joshua Tian Jin Tee · Chang Yoo
Joshua Tian Jin Tee · Hee Suk Yoon · Sunjae Yoon · Tri Ton · Chang Yoo