7 citations · 7 across the 5 of their papers we have counts for
5 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…
MultiMediate'24: Multi-Domain Engagement Estimation
Philipp Müller, Michal Balazia, Tobias Baur +8
Estimating the momentary level of participant's engagement is an important prerequisite for assistive systems that support human interactions. Previous work has addressed this task…
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…
VSA4VQA: Scaling a Vector Symbolic Architecture to Visual Question Answering on Natural Images
Anna Penzkofer, Lei Shi, Andreas Bulling
While Vector Symbolic Architectures (VSAs) are promising for modelling spatial cognition, their application is currently limited to artificially generated images and simple spatial…
Int-HRL: Towards Intention-based Hierarchical Reinforcement Learning
Anna Penzkofer, Simon Schaefer, Florian Strohm +3
While deep reinforcement learning (RL) agents outperform humans on an increasing number of tasks, training them requires data equivalent to decades of human gameplay. Recent hierar…