Technische Universität München Robotics and Embedded Systems
 

Dipl.-Inf. Thomas Rückstieß (Alumnus)

 

Former External PhD Student

E-Mail ruecksti@in.tum.de
Room HB 2.02.19
Phone +49.89.289.17632
Fax +49.89.289.18107
Address Institut für Informatik VI
Technische Universität München
Boltzmannstraße 3
85748 Garching bei München
Germany
Homepage http://www.rueckstiess.net/
 

Interests

Artificial intelligence, machine learning, reinforcement learning, policy gradients, artificial curiosity, robotics,
(recurrent) neural networks, artificial awareness, theory of mind

Curriculum Vitæ

Apr. 2006 - Today Technische Universität München
PhD Student at the chair of Robotics and Embedded Systems under Prof. Jürgen Schmidhuber
in the Machine Learning & Cognitive Robotics Group "CogBotLab".
Oct. 1999 - Mar. 2006 Eberhard Karls Universität Tübingen
Study of Bioinformatics with Emphasis on Robotics and Cognition
Aug. 2002 - Sep. 2003 University of Oregon, USA
One year exchange program with courses in Computer Science and Biology
1989 - 1998 Gymnasium Weingarten
High school with main courses in Mathematics and Chemistry

Publications

[1] Thomas Rückstieß, Christian Osendorfer, and Patrick van der Smagt. Minimizing data consumption with sequential online feature selection. International Journal of Machine Learning and Cybernetics, 4(3):235-243, 2013. [ DOI | .bib | .pdf ]
[2] Thomas Rückstieß, Christian Osendorfer, and Patrick van der Smagt. Minimizing data consumption in sequential classification. International Journal of Machine Learning and Cybernetics, 2012. [ DOI | .bib | .pdf ]
[3] Thomas Rückstieß, Christian Osendorfer, and Patrick van der Smagt. Sequential feature selection for classification. In Proceedings of the Australasian Conference on Artificial Intelligence, AI 2011, 2011. [ DOI | .bib | .pdf ]
[4] Thomas Rückstieß and Jürgen Schmidhuber. A Python Experiment Suite. The Python Papers, 6(1):2, 2011. [ .bib | .pdf ]
[5] Thomas Rückstieß and Jürgen Schmidhuber. Python Experiment Suite Implementation. The Python Papers Source Codes, 2(4), 2011. [ .bib | .pdf ]
[6] 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 ]
[7] 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 ]
[8] 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 ]
[9] Thomas Rückstieß, Martin Felder, and Jürgen Schmidhuber. State-Dependent Exploration for policy gradient methods. In W. Daelemans et al., editor, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases 2008, Part II, LNAI 5212, pages 234-249, 2008. [ .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 ]