Leon Keller

2 accepted papers

2025

Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning

Leon Keller, Daniel Tanneberg, Jan Peters

ICRA 2025

Imitation learning is a popular method for teaching robots new behaviors. However, most existing methods focus on teaching short, isolated skills rather than long, multistep tasks. To bridge this gap, imitation learning algorithms must not only learn individual skills but also an abstract understand

Cited by 7 Source ↗Scholar ↗

2020

Model-Based Quality-Diversity Search for Efficient Robot Learning

Leon Keller, Daniel Tanneberg, Svenja Stark, Jan Peters

IROS 2020poster

Despite recent progress in robot learning, it still remains a challenge to program a robot to deal with open-ended object manipulation tasks. One approach that was recently used to autonomously generate a repertoire of diverse skills is a novelty based Quality-Diversity (QD) algorithm. However, as m…

Cited by 26 Source ↗Scholar ↗