Marc Toussaint

picture Marc Toussaint
TU Berlin
Marchstr. 23, MAR 4-4
10587 Berlin, Germany
office@lis.tu-berlin.de
Admin:
Ilaria Cicchetti-Nilsson
i.cicchetti-nilsson@tu-berlin.de
tel: +49 30 314 70 140

I’m head of the Learning & Intelligent Systems Lab at the EECS Faculty of TU Berlin. I’m also member of the Science Of Intelligence cluster of excellence, and Max Plack Fellow at the MPI for Intelligent Systems.

You’re welcome to visit my Google Scholar, GitHub, ResearchGate, and arXiv sites.

Please see the top menu for Publications and Teaching material.

News

Info for Students @ TU Berlin

  • MSc/BSC requests: Students at TUB, please contact us via ISIS. We can only offer theses projects to students enrolled at TU Berlin. We cannot help external students to enroll at TU Berlin – please see here for information on how to apply for MSc/BSc programs at TU Berlin. If you have any questions, please contact Oguz, Ozgur ozgur.oguz@campus.tu-berlin.de and office@lis.tu-berlin.de

LGP demonstrations

See this page for multiple videos demonstrating Logic-Geometric Programming on various contexts (doesn’t work in Firefox for me). The methods is described in our RSS’18 publication. The bottom of the page contains the RSS demonstrations, the top more recent advances. More to come. See the github repo for code.

Max Planck Fellow

From Nov 1st 2018 I am Max Plack Fellow with the MPI for Intelligent Systems.


Positions

since 03/20 Full Prof. at TU Berlin; head of the Learning and Intelligent Systems lab.
since 11/18 Max Planck Fellow with the MPI for Intelligent Systems
08/17-07/18 Visiting Scholar at CSAIL, MIT (LIS group)
04/17-07/17 Lead of the ML-Robotics lab at Amazon, Berlin
12/12-02/20 Full Prof. at University of Stuttgart; head of the Machine Learning and Robotics Lab.
10/10-11/12 Prof. (W1) at the Department of Math and Computer Science, FU Berlin; head of the Machine Learning and Robotics Lab at FU Berlin
3/07-10/10 head of the Machine Learning and Robotics group (Emmy Noether Programme) at the IDA lab (Klaus-Robert Müller), TU Berlin.
8/06-2/07 guest scientist at the Honda Research Institute, Offenbach.
6/04-6/06 post doc at the Machine Learning group (Chris Williams) and the Statistical Machine Learning and Motor Control group (Sethu Vijayakumar), University of Edinburgh.
4/00-5/04 PhD student (& brief post doc) at the Adaptive Systems group, Institut für Neuroinformatik (Werner von Seelen), Ruhr-Universität-Bochum.
6/98-3/00 student at the Cologne gravity group (Friedrich W. Hehl), Institute for Theoretical Physics, U Cologne.


Current research interests

  • Our research focusses on the combination of decision theory and machine learning, motivated by applications in robotics. The goal are learning systems that are able to reason about their own state of knowledge (e.g., in a Bayesian way) and decide which actions might yield the most informative future data, make them learn even better and eventually solve problems. We address this in the form of Reinforcement Learning, Planning and Active Learning in probabilistic relational domains. Further, a growing focus of our lab are real-world robotic systems and joint symbolic and geometric planning, including trajectory optimization and optimal control methods.
  • 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