4 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…
High entropy leads to symmetry-equivariant policies in Dec-POMDPs
Johannes Forkel, Constantin Ruhdorfer, Michael Beukman +2
We prove that in any Dec-POMDP, sufficiently high entropy regularization ensures that the policy gradient flow with tabular softmax parametrization always converges, for any initia…
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…