Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking 文章

ArXiv CS.AI2026-05-27NEWSen作者: Haruka Kiyohara, Mihaela Curmei, Ariel Evnine, Shankar Kalyanaraman, Israel Nir, Ana-Roxana Pop, Nitzan Razin, Sarah Dean, Thorsten Joachims, Udi Weinsberg

Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking · 相关技术