Marc Deisenroth Member
Marc Deisenroth
Marc joined the group in December 2011 as a Senior Research Scienctist & Group Leader: Learning for Control.
From February 2010 to December 2011, Marc has been a full-time Research Associate in Dieter Fox' lab at the University of Washington (Seattle). Marc completed his Ph.D. at the Karlsruhe Institute for Technology (Germany) with Uwe D. Hanebeck. Marc conducted his Ph.D. research under Carl Edward Rasmussen's supervision at the Max Planck Institute for Biological Cybernetics (2006–2007) and at the University of Cambridge (2007–2009).
Marc's research interests center around methodologies from modern Bayesian statistics and their application to control and autonomous robotic systems. Marc's goal is to make robotic and control systems more autonomous by efficiently using available information.
Research Interests
- Machine Learning: Gaussian processes, Reinforcement learning, Approximate inference, Graphical models, Active learning/optimal design
- Control and Robotics: Optimal control, Legged locomotion, Robot learning
- Signal Processing: Bayesian state estimation, System identification, Inference and learning in nonlinear dynamical systems
An full list of publications can be found here.
Marc Deisenroth can be found on [Google Citations].
Key References
- Marc P. Deisenroth, Ryan Turner, Marco Huber, Uwe D. Hanebeck, Carl E. Rasmussen (2012). Robust Filtering and Smoothing with Gaussian Processes, IEEE Transactions on Automatic Control download
- Deisenroth, M.P.; Rasmussen, C.E.; Peters, J. (2009). Gaussian Process Dynamic Programming, Neurocomputing, 72, pp.1508-1524 download
- Marc P. Deisenroth, Carl E. Rasmussen (2011). PILCO: A Model-Based and Data-Efficient Approach to Policy Search, International Conference on Machine Learning (ICML 2011) download
- Marc P. Deisenroth, Carl E. Rasmussen, Dieter Fox (2011). Learning to Control a Low-Cost Robotic Manipulator Using Data-Efficient Reinforcement Learning, Robotics: Science & Systems (RSS 2011) download
- Marc P. Deisenroth (2010). Efficient Reinforcement Learning Using Gaussian Processes, in: Uwe D. Hanebeck (eds.), 9, KIT Scientific Publishing download
- Marc P. Deisenroth, Marco F. Huber, Uwe D. Hanebeck (2009). Analytic Moment-based Gaussian Process Filtering, International Conference on Machine Learning (ICML 2009) download
- Marc P. Deisenroth and Henrik Ohlsson (2011). A General Perspective on Gaussian Filtering and Smoothing: Explaining Current and Deriving new Algorithms , American Control Conference (ACC 2011) download
- Cynthia Matuszek, Brian Mayton, Robert Aimi, Marc P. Deisenroth, Liefeng Bo, Robert Chu, Mike Kung, Louis LeGrand, Joshua R. Smith and Dieter Fox (2011). Gambit: An Autonomous Chess-Playing Robotic System, International Conference on Robotics and Automation (ICRA 2011) download
News
- EWRL 2012: I'm co-organizing the 10th European Workshop on Reinforcement Learning (EWRL 2012) with Csaba Szepesvari and Jan Peters.
Contact Information
Mail: Marc Deisenroth, TU Darmstadt, FB Informatik, FG IAS, Hochschulstr. 10, 64289 Darmstadt
Office: Room E323, Robert-Piloty-Gebaeude S2|02
+49-6151-167396
+49-6151-167374
marc@ias.tu-darmstadt.de
