Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhu, Banghua, Jordan, Michael I., Jiao, Jiantao
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2401.16335