2 papers
cs.LG2025
Beyond Softmax: A New Perspective on Gradient Bandits
Emerson Melo, David Müller
We establish a link between a class of discrete choice models and the theory of online learning and multi-armed bandits. Our contributions are: (i) sublinear regret bounds for a br…
cs.RO2025
Autonomous Human-Robot Interaction via Operator Imitation
Sammy Christen, David Müller, Agon Serifi +5
Teleoperated robotic characters can perform expressive interactions with humans, relying on the operators' experience and social intuition. In this work, we propose to create auton…