I'm almost all the time in Cambridge where I work on Gaussian process models for reinforcement learning together with Carl Rasmussen (University of Cambridge) and Jan Peters (Max Planck Institute for Biological Cybernetics).

Please check my homepage in Cambridge for all research-related stuff (including papers, demos, code, ...).

Links


Publications

 
Marc Peter Deisenroth, Ryan Darby Turner, Marco F. Huber, Uwe D. Hanebeck, Carl Edward Rasmussen,
Robust Filtering and Smoothing with Gaussian Processes
IEEE Transactions on Automatic Control, 57(7):1865-1871, July 2012.
PDF URL
Author : Marc Peter Deisenroth, Ryan Darby Turner, Marco F. Huber, Uwe D. Hanebeck, Carl Edward Rasmussen
Editor :
Title : Robust Filtering and Smoothing with Gaussian Processes
In : IEEE Transactions on Automatic Control
Address :
Date : July 2012
Abstract
 
Ryan Turner, Marc Peter Deisenroth, Carl Edward Rasmussen,
System Identification in Gaussian Process Dynamical Systems
Nonparametric Bayes Workshop at NIPS 2009, Whistler, Canada, December 2009.
Author : Ryan Turner, Marc Peter Deisenroth, Carl Edward Rasmussen
Editor :
Title : System Identification in Gaussian Process Dynamical Systems
In : Nonparametric Bayes Workshop at NIPS 2009
Address : Whistler, Canada
Date : December 2009
 
Marc P. Deisenroth, Carl E. Rasmussen,
Efficient Reinforcement Learning for Motor Control
Proceedings of the 10th International PhD Workshop on Systems and Control, Hluboka nad Vltavou, Czech Republic, September 2009.
Author : Marc P. Deisenroth, Carl E. Rasmussen
Editor :
Title : Efficient Reinforcement Learning for Motor Control
In : Proceedings of the 10th International PhD Workshop on Systems and Control
Address : Hluboka nad Vltavou, Czech Republic
Date : September 2009
 
Marc Peter Deisenroth, Carl Edward Rasmussen,
Bayesian Inference for Efficient Learning in Control
Multidisciplinary Symposium on Reinforcement Learning (MSRL), Montreal, Canada, June 2009.
PDF
Author : Marc Peter Deisenroth, Carl Edward Rasmussen
Editor :
Title : Bayesian Inference for Efficient Learning in Control
In : Multidisciplinary Symposium on Reinforcement Learning (MSRL)
Address : Montreal, Canada
Date : June 2009
 
Marc P. Deisenroth, Marco F. Huber, Uwe D. Hanebeck,
Analytic Moment-based Gaussian Process Filtering
26th International Conference on Machine Learning (ICML 2009) in Montreal, Canada, June 2009.
PDF
Author : Marc P. Deisenroth, Marco F. Huber, Uwe D. Hanebeck
Editor :
Title : Analytic Moment-based Gaussian Process Filtering
In : 26th International Conference on Machine Learning (ICML 2009) in Montreal, Canada
Address :
Date : June 2009
Abstract
 
Marc P. Deisenroth, Carl E. Rasmussen, Jan Peters,
Gaussian Process Dynamic Programming
Neurocomputing, 72(7-9):1508-1524, March 2009.
PDF URL
Author : Marc P. Deisenroth, Carl E. Rasmussen, Jan Peters
Editor :
Title : Gaussian Process Dynamic Programming
In : Neurocomputing
Address :
Date : March 2009
Abstract
 
Carl E. Rasmussen, Marc P. Deisenroth,
Probabilistic Inference for Fast Learning in Control
Recent Advances in Reinforcement Learning. Proceedings of the 8th European Workshop on Reinforcement Learning (EWRL 2008), 5323:229-242, Springer-Verlag, November 2008.
PDF
Author : Carl E. Rasmussen, Marc P. Deisenroth
Editor : S. Girgin, M. Loth, R. Munos, P. Preux, D. Ryabko
Title : Probabilistic Inference for Fast Learning in Control
In : Recent Advances in Reinforcement Learning. Proceedings of the 8th European Workshop on Reinforcement Learning (EWRL 2008)
Address :
Date : November 2008
Abstract
 
Marc P. Deisenroth, Jan Peters, Carl E. Rasmussen,
Approximate Dynamic Programming with Gaussian Processes
Proceedings of the 2008 American Control Conference (ACC 2008), pp. 4480-4485, Seattle, Washington, USA, June 2008.
PDF
Author : Marc P. Deisenroth, Jan Peters, Carl E. Rasmussen
Editor :
Title : Approximate Dynamic Programming with Gaussian Processes
In : Proceedings of the 2008 American Control Conference (ACC 2008)
Address : Seattle, Washington, USA
Date : June 2008
Abstract
 
Marc P. Deisenroth, Carl E. Rasmussen, Jan Peters,
Model-Based Reinforcement Learning with Continuous States and Actions
Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008), pp. 19-24, Bruges, Belgium, April 2008.
PDF
Author : Marc P. Deisenroth, Carl E. Rasmussen, Jan Peters
Editor :
Title : Model-Based Reinforcement Learning with Continuous States and Actions
In : Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008)
Address : Bruges, Belgium
Date : April 2008
Abstract
 
Marc P. Deisenroth, Florian Weissel, Toshiyuki Ohtsuka, Uwe D. Hanebeck,
Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces
Proceedings of the 2007 European Control Conference (ECC 2007), Kos, Greece, July 2007.
PDF
Author : Marc P. Deisenroth, Florian Weissel, Toshiyuki Ohtsuka, Uwe D. Hanebeck
Editor :
Title : Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces
In : Proceedings of the 2007 European Control Conference (ECC 2007)
Address : Kos, Greece
Date : July 2007
Abstract
 
Marc P. Deisenroth, Toshiyuki Ohtsuka, Florian Weissel, Dietrich Brunn, Uwe D. Hanebeck,
Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle
Proceedings of the 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2006), pp. 371-376, Heidelberg, Germany, September 2006.
PDF
Author : Marc P. Deisenroth, Toshiyuki Ohtsuka, Florian Weissel, Dietrich Brunn, Uwe D. Hanebeck
Editor :
Title : Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle
In : Proceedings of the 2006 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2006)
Address : Heidelberg, Germany
Date : September 2006
Abstract
Personal tools