作者位次 #5/15AAAI 2026Poster· Artificial Intelligence
TAPO: Dynamic Teacher and Perturbed Answer Injection for Policy Optimization
Maowei Jiang · Zihang Wang · Qi Wang · Peter Bús · Moquan Chen · Yifan Wang · Quangao Liu · Ruiqi Li · Pengyu Zeng · Ruikai Liu · Alan Liang · Yansong Xu · Yusong Hu · Chaoran Zhang · Zhiyong Dong
强化学习与后训练OpenReview