http://dl.gi.de/handle/20.500.12116/11088 2026-07-23T10:29:07Z 2026-07-23T10:29:07Z Metzen, Jan Hendrik Fabisch, Alexander Senger, Lisa Gea Fernández, José Kirchner, Elsa Andrea http://dl.gi.de/handle/20.500.12116/11396 2018-03-20T10:33:08Z 2014-01-01T00:00:00Z

Towards Learning of Generic Skills for Robotic Manipulation Metzen, Jan Hendrik; Fabisch, Alexander; Senger, Lisa; Gea Fernández, José; Kirchner, Elsa Andrea Learning versatile, reusable skills is one of the key prerequisites for autonomous robots. Imitation and reinforcement learning are among the most prominent approaches for learning basic robotic skills. However, the learned skills are often very specific and cannot be reused in different but related tasks. In the project 'Behaviors for Mobile Manipulation', we develop hierarchical and transfer learning methods which allow a robot to learn a repertoire of versatile skills that can be reused in different situations. The development of new methods is closely integrated with the analysis of complex human behavior.

2014-01-01T00:00:00Z Siebers, Michael http://dl.gi.de/handle/20.500.12116/11395 2018-03-20T10:33:08Z 2014-01-01T00:00:00Z

Transfer of Domain Knowledge in Plan Generation: Learning Goal-dependent Annulling Conditions for Actions Siebers, Michael In this paper we present an approach to avoid dead-ends during automated plan generation. A first-order logic formula can be learned that holds in a state if the application of a specific action will lead to a dead-end. Starting from small problems within a problem domain examples of states where the application of the action will lead to a dead-end will be collected. The states will be generalized using inductive logic programming to a first-order logic formula. We will show how different notions of goal-dependence could be integrated in this approach. The formula learned will be used to speed-up automated plan generation. Furthermore, it provides insight into the planning domain under consideration.

2014-01-01T00:00:00Z Widmer, Christian Kloft, Marius Lou, Xinghua Rätsch, Gunnar http://dl.gi.de/handle/20.500.12116/11390 2018-03-20T10:33:08Z 2014-01-01T00:00:00Z

Regularization-Based Multitask Learning With Applications to Genome Biology and Biological Imaging Widmer, Christian; Kloft, Marius; Lou, Xinghua; Rätsch, Gunnar The aim of multitask learning is to improve the generalization performance of a set of related tasks by exploiting complementary information about the tasks. In this paper, we review established approaches for regularization based multitask learning, sketch some recent developments, and demonstrate their applications in Computational Biology and Biological Imaging.

2014-01-01T00:00:00Z Kudenko, Daniel http://dl.gi.de/handle/20.500.12116/11389 2018-03-20T10:33:08Z 2014-01-01T00:00:00Z

Interview with Peter Stone and Matthew E. Taylor Kudenko, Daniel

2014-01-01T00:00:00Z