Repairing Reward Functions with Feedback to Mitigate Reward Hacking

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hatgis-Kessell, Stephane, Bhamidipaty, Logan Mondal, Brunskill, Emma
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.13036