Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models.

Ashutosh Baheti Ximing Lu Faeze Brahman Ronan Le Bras 0001 Maarten Sap Mark O. Riedl Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models. 2024 ICLR https://openreview.net/forum?id=ZDGKPbF0VQ conf/iclr/2024 db/conf/iclr/iclr2024.html#BahetiLB0SR24