Joar Skalse

joarskalse's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 4 papers over 1 year ago

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification

Paper • 2403.06854 • Published Mar 11, 2024

On The Expressivity of Objective-Specification Formalisms in Reinforcement Learning

Paper • 2310.11840 • Published Oct 18, 2023

STARC: A General Framework For Quantifying Differences Between Reward Functions

Paper • 2309.15257 • Published Sep 26, 2023

Goodhart's Law in Reinforcement Learning

Paper • 2310.09144 • Published Oct 13, 2023

authored a paper over 2 years ago

Invariance in Policy Optimisation and Partial Identifiability in Reward Learning

Paper • 2203.07475 • Published Mar 14, 2022