ResearchTrend.AI
Exploring and Addressing Reward Confusion in Offline Preference Learning

Exploring and Addressing Reward Confusion in Offline Preference Learning

Xin Chen
Sam Toyer
Florian Shkurti
ArXivPDFHTML

Papers citing "Exploring and Addressing Reward Confusion in Offline Preference Learning"

1 / 1 papers shown
Title
Defining and Characterizing Reward Hacking
Defining and Characterizing Reward Hacking
Joar Skalse
Nikolaus H. R. Howe
Dmitrii Krasheninnikov
David M. Krueger
59
56
0
27 Sep 2022