Abstract
In this thesis, we discuss approaches that allow robots to learn motor skills. Motor skills can often be represented by motor primitives, which encode elemental motions. To date, there have been a number of successful applications of learning motor primitives employing imitation learning. However, many interesting motor learning problems are high-dimensional reinforcement learning problems which are often beyond the reach of current reinforcement learning methods. This thesis contributes to the state of the art in reinforcement learning applied to robotics both in terms of novel algorithms and applications. We show how motor primitives can be employed to learn motor skills on three different levels. All proposed approaches have been extensively validated with tasks such as Ball-in-a-Cup, darts, table tennis, ball throwing, or ball bouncing both in simulation, and on real robots.
About the author
Jens Kober is a postdoctoral scholar at the CoR-Lab, Bielefeld University and is working at the Honda Research Institute Europe, Germany. He received his PhD in 2012 from TU Darmstadt, Germany. From 2007-2012 he was working at the Department Schölkopf, MPI for Intelligent Systems, Germany. He has been a visiting research student at the Advanced Telecommunication Research (ATR) Center, Japan and an intern at Disney Research Pittsburgh, USA.
CoR-Lab, Bielefeld University, Universitätsstr. 25, 33615 Bielefeld, Germany, Tel.: +49-69-89011-717, Fax: +49-69-89011-749
©2014 Walter de Gruyter Berlin/Boston
