Repairing Reward Functions with Human Feedback to Mitigate Reward Hacking
Published in arXiv, 2025
By Stephane Hatgis-Kessell, Logan Mondal Bhamidipaty, and Emma Brunskill
Download here
Publications
You can also find my articles on my Google Scholar profile.
Influencing Humans to Conform to Preference Models for RLHF
Published in Arxiv Preprint, 2023
By Stephane Hatgis-Kessell, W. Bradley Knox, Serena Booth, Scott Niekum, Peter Stone
Download here
A new model of human preferences for learning reward functions
Published in UT Austin Computer Science Honors Thesis, 2023
By Stephane Hatgis-Kessell
Download here
Learning optimal advantage from preferences and mistaking it for reward
Published in Proceedings of the AAAI Conference on Artificial Intelligence, 2023
By W. Bradley Knox, Stephane Hatgis-Kessell, Sigurdur Orn Adalgeirsson, Serena Booth, Anca Dragan, Peter Stone,Scott Niekum
Download here
Models of human preference for learning reward functions
Published in Transactions on Machine Learning Research (TMLR), 2023
By W. Bradley Knox, Stephane Hatgis-Kessell, Serena Booth, Scott Niekum, Peter Stone, and Alessandro Allievi
Download here