Former Research Assistant
| sehnke@in.tum.de | |
| Room | MI 00.09.062 |
| Phone | +49.89.289.17852 |
| Fax | +49.89.289.18107 |
| Address | Institut für Informatik VI Technische Universität München Boltzmannstraße 3 85748 Garching bei München Germany |
| Homepage | http://www.vierzigundzwei.de/research/ |
Curriculum Vitæ
Frank Sehnke (born 1974 in Reutlingen): 2006 Diploma in computer science from University of Tübingen; Since 2007 Ph.D. student of Cognitive Robotics at the TUM Cogbotlab of TUM Computer Science department, working on robot/machine learning.Please see my personal page for a full CV. Part of Schmidhuber's TUM-Cogbotlab Team ("die Buam"):
Christian Osendorfer
Thomas Rückstiess
Frank Sehnke
Martin Felder
Alex Graves
Daniel Weiss
Recent Work:
Developing machine learning techniques for more robust behaviors of sophisticated robots like the Jonny biped robot or the CCRL robot.
Courses & Seminars:
- Hauptseminar Evolutionary Algorithms by Dipl.-Inf. Frank Sehnke (ECTS: 4.0, SWS: 2)
Publications
| [1] | Jakob Engel, Markus Holzer, Oliver Ruepp, and Frank Sehnke. On computer integrated rationalized crossword puzzle manufacturing. In Evangelos Kranakis, Danny Krizanc, and Flaminia Luccio, editors, Fun with Algorithms, volume 7288 of Lecture Notes in Computer Science, pages 131-141. Springer Berlin Heidelberg, 2012. [ DOI | .bib | .pdf ] |
| [2] | Anton Kaifel, Martin Felder, and Frank Sehnke. Improving physical wind power forecasts with recurrent or deep neural networks, 2011. [ .bib | .pdf ] |
| [3] | Mandy Grüttner, Frank Sehnke, Tom Schaul, and Jürgen Schmidhuber. Multi-dimensional deep memory atari go-player for parameter exploring policy gradients. In W. Duch K. Diamantaras and L. Iliadis, editors, Proceedings of the International Conference on Artificial Neural Networks, ICANN 2010. Springer-Verlag Berlin Heidelberg, 2010. [ .bib | .pdf ] |
| [4] | Thomas Rückstieß, Frank Sehnke, Tom Schaul, Daan Wierstra, Sun Yi, and Jürgen Schmidhuber. Exploring parameter space in reinforcement learning. Paladyn Journal of Behavioral Robotics, 1(1):14-24, 2010. [ DOI | .bib | .pdf ] |
| [5] | Ulrich Rührmair, Frank Sehnke, Jan Sölter, Srini Devadas, and Jürgen Schmidhuber. Modeling attacks on physical unclonable functions. In Proceedings of the 17th ACM Conference on Computer and Communications Security, ACM CCS 2010, 2010. [ DOI | .bib | .pdf ] |
| [6] | Tom Schaul, Justin Bayer, Daan Wierstra, Yi Sun, Martin Felder, Frank Sehnke, Thomas Rückstieß, and Jürgen Schmidhuber. PyBrain. Journal of Machine Learning Research, 2010. [ .bib | .pdf ] |
| [7] | Frank Sehnke, Christian Osendorfer, Thomas Rückstieß, Alex Graves, Jan Peters, and Jürgen Schmidhuber. Parameter-exploring policy gradients. Neural Networks, 23(2), 2010. [ DOI | .bib | .pdf ] |
| [8] | Frank Sehnke, Christian Osendorfer, Jan Sölter, Jürgen Schmidhuber, and Ulrich Rührmair. Policy gradients for cryptanalysis. In K. Diamantaras, W. Duch, and L. Iliadis, editors, Proceedings of the International Conference on Artificial Neural Networks, ICANN 2010. Springer-Verlag Berlin Heidelberg, 2010. [ DOI | .bib | .pdf ] |
| [9] | Frank Sehnke, Alex Graves, Christian Osendorfer, and Jürgen Schmidhuber. Multimodal parameter-exploring policy gradients. In Bob Werner, editor, Proceedings of the ninth International Conference on Machine Learning and Applications, ICMLA 2010, 2010. [ DOI | .bib | .pdf ] |
| [10] | Thomas Rückstieß, Martin Felder, Frank Sehnke, and Jürgen Schmidhuber. Robot learning with state-dependent exploration. In 1st International Workshop on Cognition for Technical Systems, 2008. [ .bib | .pdf ] |
| [11] | Frank Sehnke, Christian Osendorfer, Thomas Rückstieß, Alex Graves, Jan Peters, and Jürgen Schmidhuber. Policy gradients with parameter-based exploration for control. In J. Koutnik V. Kurkova, R. Neruda, editor, Proceedings of the International Conference on Artificial Neural Networks, ICANN 2008, Part I, LNCS 5163, pages 387-396. Springer-Verlag Berlin Heidelberg, 2008. [ .bib | .pdf ] |
| [12] | Frank Sehnke, Thomas Rückstieß, Martin Felder, and Jürgen Schmidhuber. Parametric policy gradients for robotics. In 1st International Workshop on Cognition for Technical Systems, 2008, 2008. [ .bib | .pdf ] |
| [13] | Patrick Heinemann, Frank Sehnke, Felix Streichert, and A. Zell. Towards a calibration-free robot: The ACT algorithm for automatic online color training. In Robot Soccer World Cup X. Springer-Verlag Berlin Heidelberg, 2007. [ .bib | .pdf ] |
| [14] | Patrick Heinemann, Frank Sehnke, Felix Streichert, and A. Zell. An automatic approach to online color training in robocup environments. In Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2006, 2006. [ .bib | .pdf ] |
| [15] | Patrick Heinemann, Frank Sehnke, Felix Streichert, and A. Zell. Automatic calibration of camera to world mapping in robocup using evolutionary algorithms. In Proceedings of the IEEE International Congress on Evolutionary Computing, CEC 2006, 2006. [ .bib | .pdf ] |