Prof. Dr. rer. nat.

Marc Toussaint

Principal Investigator (EXC)
Institut für Parallele und Verteilte Systeme


+49 711 685-88376


Universitätsstraße 38
70569 Stuttgart
Raum: 2.225


  • Combination of decision theory and machine learning,
  • Research in the intersections of modern AI (probabilistic reasoning, learning & planning), robotics and machine learning
  • Probabilistic approaches to planning, on symbolic (relational) as well as motion & control level
  • (Constrained) Optimization methods for robotics, reinforcement learning and machine learning in general
  • Active learning, experimental design and UCB/UCT type methods for autonomous (e.g.\ robot) exploration of complex domains
  • General Machine Learning: learning representations, Bayesian networks & graphical models

Ausgewählte Publikationen

  1. P. Englert and M. Toussaint. “Combined Optimization and Reinforcement Learning for Manipulation Skills”. In: Proceedings of Robotics: Science and Systems (R:SS 2016). 2016.
  2. M. Toussaint. “A tutorial on Newton methods for constrained trajectory optimization and relations to SLAM, Gaussian Process smoothing, optimal control, and probabilistic inference”. In: Geometric and Numerical Foundations of Movements. Springer, 2016.
  3. M. Toussaint, T. Munzer, Y. Mollard, L. Y. Wu, N. A. Vien, and M. Lopes. “Relational Activity Processes for Modeling Concurrent Cooperation”. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA 2016) (2016).
  4. A. Kumar, S. Zilberstein, and M. Toussaint. “Probabilistic Inference Techniques for Scalable Multiagent Decision Making”. In: Journal of Artificial Intelligence Research 53 (2015), pp. 223–270.
  5. M. Toussaint. “Logic-Geometric Programming: An Optimization-Based Approach to Combined Task and Motion Planning”. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI 2015). 2015.
  6. N. Jetchev and M. Toussaint. “Fast Motion Planning from Experience: Trajectory Prediction for Speeding up Movement Generation”. In: Autonomous Robots 34.1–2 (2013), pp. 111–127.
  7. M. Botvinick and M. Toussaint. “Planning as probabilistic inference”. In: Trends in Cognitive Sciences 16 (2012), pp. 485–488.
  8. T. Lang, M. Toussaint, and K. Kersting. “Exploration in Relational Domains for Model-based Reinforcement Learning”. In: Journal of Machine Learning Research 13 (2012), pp. 3691–3734.
  9. K. Rawlik, M. Toussaint, and S. Vijayakumar. “On Stochastic Optimal Control and Reinforcement Learning by Approximate Inference”. In: Proceedings of of Robotics: Science and Systems (R:SS 2012) (2012).
  10. T. Lang and M. Toussaint. “Planning with Noisy Probabilistic Relational Rules”. In: Journal of Artificial Intelligence Research 39.1 (2010), pp. 1–49.

2017–2018 Visiting Researcher, Massachusetts Institute of Technology, USA

since 12/2012
Full Prof. at University of Stuttgart; head of the Machine Learning and Robotics Lab

Prof. (W1) at the Department of Math and Computer Science, FU Berlin; head of the Machine Learning and Robotics Lab at FU Berlin

Head of the Machine Learning and Robotics group (Emmy Noether Programme) at the IDA lab (Klaus-Robert Müller), TU Berlin

Guest scientist at the Honda Research Institute, Offenbach

Post doc at the Machine Learning group (Chris Williams) and the Statistical Machine Learning and Motor Control group (Sethu Vijayakumar), University of Edinburgh

PhD student (& brief post doc) at the Adaptive Systems group, Institut für Neuroinformatik (Werner von Seelen), Ruhr-Universität-Bochum

Student at the Cologne gravity group (Friedrich W. Hehl), Institute for Theoretical Physics, U Cologne


Ausbildung und Akademische Grade

  • 2003 Dr.rer.nat., Institute for Neuroinformatics, Ruhr-Universität Bochum
  • 1999 Diploma in Physics, University of Cologne
  • 1996 Pre-Diploma in Mathematics, University of Cologne
  • 1994–1999 Study of Physics and Mathematics, University of Cologne
  • 2012 Best Paper Runner Up Awards at R:SS 2012
  • 2008 Best Paper Runner Up Award at UAI 2008
  • 2007 Best Paper Award at ICMLA 2007
  • 2007 DFG Emmy Noether Fellowship for an independent research group
  • Area Chair for R:SS (2013, 2014)
  • Invited tutorials (selection): Machine Learning Summer School 2013 (Tübingen), Int. Conf. On Robots: Science and Systems 2012, Int. Conf. on Machine Learning 2011
  • Coordinator of the DFG SPP 1527 “Autonomous Learning” (since 2011)
  • Editorial Board member of “Journal of AI Research” (JAIR) (since 2011)
  • Senior Program Committee Member IJCAI (2011, 2017)
  • Associate Editor for “ICRA” (2010–2013)
  • Vice Spokesperson of the DFG GRK 1589 “Sensory Computation in Neural Systems” (2010–2012)
  • Steering Committee of IEEE Technical Committee on Robot Learning (since 2009)
  • Regularly reviewing for the top journals JAIR, IJRR, JMLR, TRO, AuRo
  • Regularly reviewing for DFG
Zum Seitenanfang