Litcius/Paper detail

Defining and Characterizing Reward Hacking

Nikolaus Howe, Dmitrii Krasheninnikov, David Krueger, Joar Skalse

20227 citationsDOI

Topics & Concepts

Data Visualization and AnalyticsSafety Warnings and SignageInformation and Cyber Security
Defining and Characterizing Reward Hacking | Litcius