⚠️ The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
By Lukas Fluri*, @leon-lang.bsky.social *, Alessandro Abate, Patrick Forré, David Krueger, Joar Skalse
📜 arxiv.org/abs/2406.15753
🧵6 / 8
The official account of the Amsterdam Machine Learning Lab (AMLab) at UvA, co-directed by Max Welling and Jan-Willem van de Meent.