The acquisition and self-improvement of novel motor skills is among the most important problems in robotics.

I will discuss various learning techniques we developed that enable robots to have complex interactions with their environment and humans. Complexity arises from dealing with highdimensional input data, non-linear dynamics in general and contacts in particular, multiple reference frames, and variability in objects, environments, and tasks. A human teacher is always involved in the learning process, either directly (providing data) or indirectly (designing the optimization criterion), which raises the question: How to best make use of the interactions with the human teacher to render the learning process efficient and effective?

TU Delft:

• Jens Kober