7 papers
Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
Constantin Ruhdorfer, Matteo Bortoletto, Victor Oei +2
We introduce Unsupervised Partner Design (UPD), a population-free multi-agent reinforcement learning method for robust ad-hoc teamwork. UPD generates training partners on-the-fly a…
Ontology-Guided Diffusion for Zero-Shot Visual Sim2Real Transfer
Mohamed Youssef, Mayar Elfares, Anna-Maria Meer +2
Bridging the simulation-to-reality (sim2real) gap remains challenging as labelled real-world data is scarce. Existing diffusion-based approaches rely on unstructured prompts or sta…
The Yokai Learning Environment: Tracking Beliefs Over Space and Time
Constantin Ruhdorfer, Matteo Bortoletto, Johannes Forkel +2
The ability to cooperate with unknown partners is a central challenge in cooperative AI and widely studied in the form of zero-shot coordination (ZSC), which evaluates an algorithm…
ToM-SSI: Evaluating Theory of Mind in Situated Social Interactions
Matteo Bortoletto, Constantin Ruhdorfer, Andreas Bulling
Most existing Theory of Mind (ToM) benchmarks for foundation models rely on variations of the Sally-Anne test, offering only a very limited perspective on ToM and neglecting the co…
The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design
Constantin Ruhdorfer, Matteo Bortoletto, Anna Penzkofer +1
We introduce the Overcooked Generalisation Challenge (OGC) - a new benchmark for evaluating reinforcement learning (RL) agents on their ability to cooperate with unknown partners i…
ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback
Matteo Bortoletto, Yichao Zhou, Lance Ying +2
While humans are inherently social creatures, the challenge of identifying when and how to assist and collaborate with others - particularly when pursuing independent goals - can h…