As artificial intelligence reshapes our digital world at a breathtaking pace, a curious question arises: Where are all the real-world, intelligent robots? While we have mastered the generation of text, images, and video by leveraging vast web-scale datasets, robotics still faces a fundamental data bottleneck. Reinforcement learning (RL) offers a compelling solution, enabling agents to learn autonomously by collecting their own experience. However, the path to autonomy is often blocked by the staggering inefficiency of current RL algorithms, which can require millions of trials to master simple tasks. This talk embarks on a quest to tackle this efficiency problem head-on. I will argue that a crucial step toward unlocking the potential of robot learning lies in a two-pronged approach: first, by developing statistically efficient algorithms that can reuse data by leveraging sound off-policy techniques, and second, by designing better action representations for physical, real-world agents. By making our algorithms more efficient and refining their core hypotheses, we can accelerate the journey toward real embodied artificial intelligence.

The flexibility and robustness of current robots is limited by their lack of understanding of their environment. For this reason, most robots operate in controlled environments. Machine learning can circumvent modeling problems but introduces new problems of generalizing from examples. How can robots acquire understanding (of structure, function, causality, etc.) that allows them to generalize from sparse experience? Motivated by shortcomings of current machine-learning methods, I will argue that "understanding" is a meaningful notion in AI that reaches beyond prediction and control. I will discuss examples of our recent work on learning visual relational concepts, extrapolation of learned movements beyond the training distribution, learning of symbolic concepts and rules, and structure-driven skill learning from sensorimotor experience. Our long-term objective is to improve abstraction, generalization, robustness, and ultimately explainability of robot perception and action.

Künstliche Intelligenz" bezeichnet derzeit Systeme, die auf maschinellem Lernen (ML) basieren. Dieser Workshop führt in die Grundlagen des ML ein, mit besonderem Augenmerk auf neuronale Netze, der derzeit populärsten ML-Technologie. Darauf aufbauend vermittelt er ein Grundverständnis für prinzipielle Möglichkeiten und Grenzen von ML und warum es mit derzeitigen Mitteln extrem schwierig ist, Diskriminierung in KI-Systemen zu verhindern.