arXiv - CSCL: "Improving Reinforcement Learning from Human Feedb…" - CleverLibre Social

arXiv - CSCL @arxiv_cscl@social.cleverlibre.org

Improving Reinforcement Learning from Human Feedback with Efficient Reward Model Ensemble. (arXiv:2401.16635v1 [cs.LG])

http://arxiv.org/abs/2401.16635 #arXiv #NLProc

Jan 31, 2024, 03:18 · · arxiv-cscl · · ·

Sign in to participate in the conversation