Joar Max Viktor Skalse

7 papers · 2023–2025 · 3 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (3) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (13)

Conferences

ICLR (4) ICML (2) AAAI (1)

Top co-authors

Alessandro Abate (5) Charlie Griffin (2) Adam Gleave (2) Klaus Kiendlhofer (1) Halfdan Holm (1) David Krueger (1) Erik Jenner (1) Lukas Fluri (1) Leon Lang (1) Patrick Forré (1)

Keywords

reward function (2) partial identifiability (2) preference inference (1) reward learning (1) expert demonstration (1) policy optimisation (1) game theory (1) hyperbolic discounting (1) inverse reinforcement learning (1)

Papers

Partial Identifiability in Inverse Reinforcement Learning for Agents with Non-Exponential Discounting AAAI 2025

The Perils of Optimizing Learned Reward Functions: Low Training Error Does Not Guarantee Low Regret ICML 2025

On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning ICLR 2024

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification ICLR 2024

STARC: A General Framework For Quantifying Differences Between Reward Functions ICLR 2024

Goodhart's Law in Reinforcement Learning ICLR 2024

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning ICML 2023