SPARD: Self-Paced Curriculum for RL Alignment via Integrating Reward Dynamics and Data Utility.
Xuyang Zhi, Peilun Zhou, Chengqiang Lu, Hang Lv, Yiwei Liang, Rongyang Zhang, Yan Gao, Yi Wu, Yao Hu, Hongchao Gu, Defu Lian, Hao Wang, Enhong Chen
Browse the full ACL paper archive.