作者位次 #6/12NeurIPS 2026Poster
AsyncOPD: How Stale Can On-Policy Distillation Be?
Wonjun Kang · Kevin Galim · Seunghyuk Oh · Minjun Kang · Sanghyun Park · Donghoon Kim · Minjae Lee · Minseo Kim · Rishabh Tiwari · Yuchen Zeng · HYUNG IL KOO · Kangwook Lee
强化学习与后训练OpenReview