Joar Max Viktor Skalse

Venues

Frequent coauthors

Papers

1. Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting
   AAAI 2025 · Joar Max Viktor Skalse
2. The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret
   ICML 2025 ·

   Lukas Fluri

   DBLP profile ↗ORCID search ↗
3. Goodhart's Law in Reinforcement Learning
   ICLR 2024 ·

   Jacek Karwowski

   DBLP profile ↗ORCID search ↗
4. On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
   ICLR 2024 ·

   Rohan Subramani

   DBLP profile ↗ORCID search ↗
5. Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
   ICLR 2024 · Joar Max Viktor Skalse
6. STARC: A General Framework For Quantifying Differences Between Reward Functions
   ICLR 2024 · Joar Max Viktor Skalse