|
Dipl.-Inf. Jan Hendrik Metzen jhm@informatik.uni-bremen.de
Research Assistant |
|
Research
-
Reinforcement Learning
Working on developing new means for skill discovery and learning of motor pimitives and combining those in a Hierarchical Reinforment Learning method. Developed the graph-based skill discovery method OGAHC. Furthermore, we are developing an integrated experimental platform, the Maja Machine Learning Framework ( MMLF), which simplifies empirical evaluations in Reinforcement Learning. This work is part of the BesMan project.
[Relevant publications] [MMLF] -
Brain Computer Interfaces
We use supervised machine learning techniques to detect event-related potentials (ERPs) in a human's electroencephalogram (EEG) that indicate that the human has perceived and recognized important messages that have been presented to him or that he intends to execute a movement shortly. My work in the VI-Bot and IMMI project was focused mainly on investigating how the system can detect these ERPs with a minimum amount of labeled training data from the current user by reusing data from historic sessions of the same and other users.
[Relevant publications] -
Neuroevolution
We have developed a new neuroevolutionary method called Evolutionary Acquisition of Neural Topologies (EANT) and a new genetic encoding, the common genetic encoding (CGE). We have proved certain theoretical properties of the encoding and have conducted empirical evaluations of EANT in different Reinforcement Learning problems.
[Relevant publications] -
Graph Matching
We have used methods from structural pattern recognition to develop means to automatically determine suitable landmarks in three-dimensional images (CT, MRT) of liver and lung that allow to registrate images of the same organ taken at different points in time or with different modalities. For this, we have developed new approaches for matching vessel trees extracted from the images and used the associated tree branching points as landmarks. This work was mainly done as part of my diploma thesis at the "Computer Vision and Pattern Recognition Group" of the University of Muenster and in cooperation with MeVis Research (now Fraunhofer MEVIS).
[Relevant publications] - See also my Google Scholar page here
Short CV
- 2013 - present: Team Leader "Learning" of the Robotics Research Group, University Bremen
- 2008 - present: Organizer of workgroup "Machine Learning and Optimization" of the Robotics Research Group, University Bremen
- 2009 - present: Research assistant in the Robotics Research Group, University of Bremen
- 2007 - 2009: Researcher at the Robotics Innovation Center, German Research Center for Artificial Intelligence (DFKI, Bremen)
- 2006 - 2007: Research assistant in the Robotics Research Group, University of Bremen
- 2006: Diploma in Computer Science
- 2004 - 2006: Scholarship of "Studienstiftung des Deutschen Volkes" (German National Academic Foundation)
- 2001 - 2006: Study of "Computer Science" at Westfaelische Wilhelms-University, Muenster, Germany
Teaching
-
Summer term 2013
Reinforcement Lernen -
Winter term 2012/2013
Lernverfahren fuer autonome Roboter -
Summer term 2012
Reinforcement Lernen -
Winter term 2011/2012
Lernverfahren fuer autonome Roboter -
Summer term 2011
Reinforcement Lernen -
Winter term 2010/2011
Maschinelles Lernen fuer autonome Roboter 2 -
Sommer term 2010
Maschinelles Lernen fuer autonome Roboter 1 -
Winter term 2009/2010
Maschinelles Lernen fuer autonome Roboter 2
Software
- MMLF:
The Maja Machine Learning Framework (MMLF) is a general framework for problems in the domain of Reinforcement Learning (RL) written in python. It provides a set of RL related algorithms and a set of benchmark domains. Furthermore it is easily extensible and allows to automate benchmarking of different agents. Among the RL algorithms are TD(lambda), CMA-ES, Fitted R-Max, Monte-Carlo learning, the DYNA-TD and the actor-critic architecture. MMLF contains different variants of the maze-world and pole-balancing problem class as well as the mountain-car testbed and the pinball maze domain.
Community
- Program committee of 5th International Workshop on Evolutionary and Reinforcement Learning for Autonomous Robot Systems (ERLARS 2012)
- 2013: Reviewer of the Journal of Machine Learning Research (JMLR)
- 2009: Reviewer of the Image and Vision Computing Journal (IVC)