Skip to content
conftrace_
2025 ICML ICML 2025

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Reinforcement Learning

Authors

Lukas Fluri, Leon Lang, Alessandro Abate, Patrick Forré, David Krueger, Joar Max Viktor Skalse

Topics

Artificial Intelligence > Core AI > AI Safety Machine Learning > Optimization & Theory > Learning Theory Reinforcement Learning > Methods > Deep RL

Keywords

optimization generalization reward model distributional shift policy regret expected test error
Download PDF