Research on Learning Systems and Autonomous Agents

Science on learning systems is typically framed with the term machine learning. In contrast to learning in human or biological systems, the field of machine learning aims at developing algorithms that can learn from given data or from experience gained during autonomous interaction with the environment and, in so doing, at least partially mimic the way humans learn. Machine learning has become one of the major sub-disciplines of artificial intelligence, also due to its importance for efficient data analysis needed in times where big amounts of data accumulate in many domains.The field of machine learning is typically divided into three categories: Supervised learning, unsupervised learning, and reinforcement learning.

The sub-apges to this page contain a selection of learning-related projects, where the technical focus has been on:

  • reinforcement learning and single-agent learning
  • supervised learning and function approximation
  • probabilistic inference and case-based reasoning.