Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset.

Yiqin Yang, Quanwei Wang, Chenghao Li, Hao Hu, Chengjie Wu, Yuhua Jiang, Dianyu Zhong, Ziyou Zhang, Qianchuan Zhao, Chongjie Zhang, Bo Xu

Browse the full ICLR paper archive.