Quick Links

Contact

Jens Kober

Address:	Spemannstr. 38 72076 Tübingen
Room number:	238
Phone:	+49 7071 601 548
Fax:	+49 7071 601 552
E-Mail:	jens.kober

Jens Kober

Position: PhD Student Unit: Alumni Schölkopf

Overview
Curriculum Vitae
Publications

Jens Kober is currently working towards a Ph.D. in the area of motor skill learning with a strong focus on learning motor primitives and on reinforcement learning.

Please refer to http://www.robot-learning.de/Member/JensKober for more details.

ICRA 2010 Video

ICRA 2009 Video

NIPS 2008 Videos

IROS 2008 Video

Please refer to http://www.robot-learning.de/Member/CVJensKober.

Articles (7):
•	Kober J , Wilhelm A , Oztop E and Peters J (2012) Reinforcement learning to adjust parametrized motor primitives to new situations Autonomous Robots 33(4) 361-379.
•	Mülling K , Kober J , Kroemer O and Peters J (2012) Learning to Select and Generalize Striking Movements in Robot Table Tennis International Journal of Robotics Research . accepted
•	Mülling K , Kober J and Peters J (2011) A biomimetic approach to robot table tennis Adaptive Behavior 19(5) 359-376.
•	Kober J and Peters J (2011) Policy Search for Motor Primitives in Robotics Machine Learning 84(1-2) 171-203.
•	Peters J , Kober J and Schaal S (2010) Algorithmen zum Automatischen Erlernen von Motorfähigkeiten at - Automatisierungstechnik 58(12) 688-694.
•	Kober J and Peters J (2010) Imitation and Reinforcement Learning IEEE Robotics and Automation Magazine 17(2) 55-62.
•	Peters J and Kober J (2009) Policy Search for Motor Primitives KI - Zeitschrift Künstliche Intelligenz 23(3) 38-40.
Conference papers (22):
•	Kober J , Mülling K and Peters J (2012) Learning Throwing and Catching Skills IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012).
•	Mülling K , Kober J , Kroemer O and Peters J (2012) Learning to Select and Generalize Striking Movements in Robot Table Tennis AAAI 2012 Fall Symposium on Robots Learning Interactively from Human Teachers.
•	Peters J , Kober J , Mülling K , Nguyen-Tuong D and Kroemer O (2012) Robot Skill Learning 20th European Conference on Artificial Intelligence (ECAI 2012), 1-6.
•	Kober J and Peters J (2011) Learning elementary movements jointly with a higher level task (Ed) Amato, N.M., IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), IEEE, Piscataway, NJ, USA, 338-343.
•	Kober J , Oztop E and Peters J (2011) Reinforcement Learning to adjust Robot Movements to New Situations In: Robotics: Science and Systems VI, (Ed) Matsuoka, Y. , H. F. Durrant-Whyte, J. Neira, 2010 Robotics: Science and Systems Conference (RSS 2010), MIT Press, Cambridge, MA, USA, 33-40.
•	Kober J , Oztop E and Peters J (2011) Reinforcement Learning to adjust Robot Movements to New Situations (Ed) Walsh, T., Twenty-Second International Joint Conference on Artificial Intelligence (IJCAI 2011), AAAI Press, Menlo Park, CA, USA, 2650-2655.
•	Boularias A , Kober J and Peters J (2011) Relative Entropy Inverse Reinforcement Learning In: JMLR Workshop and Conference Proceedings Volume 15: AISTATS 2011, (Ed) Gordon, G. , D. Dunson, M. Dudík, Fourteenth International Conference on Artificial Intelligence and Statistics, MIT Press, Cambridge, MA, USA, 182-189.
•	Peters J , Mülling K , Kober J , Nguyen-Tuong D and Kroemer O (2011) Towards Motor Skill Learning for Robotics In: Robotics Research, (Ed) Pradalier, C. , R. Siegwart, G. Hirzinger, 14th International Symposium on Robotics Research (ISRR 2009), Springer, Berlin, Germany, 469-482.
•	Mülling K , Kober J and Peters J (2010) Learning Table Tennis with a Mixture of Motor Primitives 10th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2010), IEEE, Piscataway, NJ, USA, 411-416.
•	Mülling K , Kober J and Peters J (2010) A biomimetic approach to robot table tennis 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), IEEE, Piscataway, NJ, USA, 1921-1926.
•	Peters J , Kober J , Mülling K , Krömer O , Nguyen-Tuong D , Wang Z , Rodriguez Gomez M and Grosse-Wentrup M (2010) Learning as a key ability for Human-Friendly Robots 3rd Workshop for Young Researchers on Human-Friendly Robotics (HFR 2010), 1-2.
•	Mülling K , Kober J and Peters J (2010) Simulating Human Table Tennis with a Biomimetic Robot Setup In: From Animals to Animats 11, (Ed) Doncieux, S. , B. Girard, A. Guillot, J. Hallam, J.-A. Meyer, J.-B. Mouret, 11th International Conference on Simulation of Adaptive Behavior (SAB 2010), Springer, Berlin, Germany, 273-282.
•	Kober J , Mülling K , Krömer O , Lampert CH , Schölkopf B and Peters J (2010) Movement Templates for Learning of Hitting and Batting 2010 IEEE International Conference on Robotics and Automation (ICRA 2010), IEEE, Piscataway, NJ, USA, 853-858.
•	Peters J , Mülling K and Kober J (2010) Experiments with Motor Primitives to learn Table Tennis In: Experimental Robotics, (Ed) Khatib, O. , V. Kumar, G. Sukhatme, 12th International Symposium on Experimental Robotics (ISER 2010), Springer, Berlin, Germany, 1-13.
•	Kober J and Peters J (2009) Learning new basic Movements for Robotics In: AMS 2009, (Ed) Dillmann, R. , J. Beyerer, C. Stiller, M. Zöllner, T. Gindele, Autonome Mobile Systeme 2009, Springer, Berlin, Germany, 105-112.
•	Kober J and Peters J (2009) Policy Search for Motor Primitives in Robotics In: Advances in neural information processing systems 21, (Ed) Koller, D. , D. Schuurmans, Y. Bengio, L. Bottou, Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS 2008), Curran, Red Hook, NY, USA, 849-856.
•	Chiappa S , Kober J and Peters J (2009) Using Bayesian Dynamical Systems for Motion Template Libraries In: Advances in neural information processing systems 21, (Ed) Koller, D. , D. Schuurmans, Y. Bengio, L. Bottou, Twenty-Second Annual Conference on Neural Information Processing Systems (NIPS 2008), Curran, Red Hook, NY, USA, 297-304.
•	Kober J and Peters J (2009) Learning motor primitives for robotics IEEE International Conference on Robotics and Automation (ICRA '09), IEEE Service Center, Piscataway, NJ, USA, 2112-2118.
•	Peters J and Kober J (2009) Using reward-weighted imitation for robot Reinforcement Learning In: IEEE ADPRL 2009, 2009 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning, IEEE Service Center, Piscataway, NJ, USA, 226-232.
•	Gomez Rodriguez M , Kober J and Schölkopf B (2009) Denoising photographs using dark frames optimized by quadratic programming First IEEE International Conference on Computational Photography (ICCP 2009), IEEE, Piscataway, NJ, USA, 1-9.
•	Peters J , Kober J and Nguyen-Tuong D (2008) Policy Learning: A Unified Perspective with Applications in Robotics In: EWRL 2008, (Ed) Girgin, S. , M. Loth, R. Munos, P. Preux, D. Ryabko, 8th European Workshop on Reinforcement Learning, Springer, Berlin, Germany, 220-228.
•	Kober J , Mohler B and Peters J (2008) Learning Perceptual Coupling for Motor Primitives In: IROS 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE Service Center, Piscataway, NJ, USA, 834-839.
Contributions to books (2):
•	Kober J and Peters J : Reinforcement Learning in Robotics: A Survey, 579-610. In: Reinforcement Learning, (Ed) M Wiering and M Otterlo, Springer, Berlin, Germany, (2012).
•	Kober J , Mohler B and Peters J : Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling, 209-225. In: From Motor Learning to Interaction Learning in Robots, (Ed) Sigaud, O. , J. Peters, Springer, Berlin, Germany, (2010).
Posters (2):
•	Peters J , Kober J and Nguyen-Tuong D (2008): Policy Learning: A Unified Perspective With Applications In Robotics, 8th European Workshop on Reinforcement Learning for Robotics (EWRL 2008), 8 10.
•	Kober J and Peters J (2008): Reinforcement Learning of Perceptual Coupling for Motor Primitives, 8th European Workshop on Reinforcement Learning for Robotics (EWRL 2008), 8 16.
Theses (2):
•	Kober J : Learning Motor Skills: From Algorithms to Robot Experiments, Technische Universität Darmstadt, (2012). PhD thesis
•	Kober J : Reinforcement Learning for Motor Primitives, University of Stuttgart, Stuttgart, Germany, (2008). Diplom thesis
Talks (2):
•	Kober J and Peters J (2010): Learning Motor Primitives for Robotics, EVENT Lab: Reinforcement Learning in Robotics and Virtual Reality, Barcelona, Spain.
•	Kober J , Peters J and Oztop E (2009): Learning Motor Primitives for Robotics, Advanced Telecommunications Research Center ATR, Kyoto, Japan.