作者位次 #2/10ICML 2026Poster· Reinforcement Learning / Online
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
Haruka Kiyohara · Mihaela Curmei · Ariel Evnine · Shankar Kalyanaraman · Israel Nir · Ana-Roxana Pop · Nitzan Razin · Sarah Dean · Thorsten Joachims · Udi Weinsberg