Published several peer-reviewed papers such as 'Choosing What Game to Play without Selecting Equilibria: Inferring Safe (Pareto) Improvements in Binary Constraint Structures' (TARK 2025), 'Observation Interference in Partially Observable Assistance Games' (ICML 2025), and others; also has a number of working papers.
Research Experience
Caspar conducts research at Carnegie Mellon University, working on multiple projects, including several papers co-authored with his advisor, Vincent Conitzer.
Education
PhD in Computer Science, Carnegie Mellon University, Advisor: Vincent Conitzer.
Background
Caspar Oesterheld is a Computer Science PhD student at Carnegie Mellon University, supervised by Vincent Conitzer. He is interested in foundational topics in theoretical computer science, game theory, and AI safety.