作者位次 #2/8ICML 2026Poster· Reinforcement Learning / Batch/Offline
BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
Yunpeng Qing · Yixiao Chi · Shuo Chen · Shunyu Liu · Kexuan Zhou · Sixu Lin · Litao Liu · Changqing Zou
强化学习与后训练OpenReview