Marc Deisenroth's Homepage
CS&E logo University of Washington Computer Science & Engineering
 
University of Washington Department of Computer Science & Engineering Marc Deisenroth
 


Home Publications Downloads Talks Links Vita

Pre-prints

  1. MP Deisenroth and H Ohlsson
    A Probabilistic Perspective on Gaussian Filtering and Smoothing
    on arXiv

Publications

2012

  1. MP Deisenroth, R Turner, M Huber, UD Hanebeck, and CE Rasmussen
    Robust Filtering and Smoothing with Gaussian Processes
    IEEE Transactions on Automatic Control
    details

2011

  1. MP Deisenroth, D Fox, and CE Rasmussen
    Learning in Robotics using Bayesian Nonparametrics
    NIPS Workshop on Bayesian Nonparametrics , Granada, Spain
    details
  2. MP Deisenroth and D Fox
    Multiple-Target Reinforcement Learning with a Single Policy
    ICML-2011 Workshop on Planning and Acting with Uncertain Models , Bellevue, WA, USA
    details
  3. MP Deisenroth, CE Rasmussen, and D Fox
    Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning
    Proceedings of the International Conference on Robotics: Science & Systems (R:SS 2011) , Los Angeles, CA, USA
    details
  4. MP Deisenroth and CE Rasmussen
    PILCO: A Model-Based and Data-Efficient Approach to Policy Search
    28th International Conference on Machine Learning (ICML 2011) , Bellevue, WA, USA
    details
  5. MP Deisenroth and H Ohlsson
    A General Perspective on Gaussian Filtering and Smoothing: Explaining Current and Deriving new Algorithms
    2011 American Control Conference (ACC 2011) , San Francisco, CA, USA
    details
  6. C Matuszek, B Mayton, R Aimi, MP Deisenroth, L Bo, R Chu, M Kung, L LeGrand, JR Smith, and D Fox
    Gambit: An Autonomous Chess-Playing Robotic System
    2011 IEEE International Conference on Robotics and Automation (ICRA 2011) , Shanghai, China
    details

2010

  1. MP Deisenroth
    Efficient Reinforcement Learning using Gaussian Processes
    Karlsruhe Series on Intelligent Sensor-Actuator-Systems , KIT Scientific Publishing, Karlsruhe, Germany.
    download (original)
    details (slightly revised, with working hyperlinks)
  2. MP Deisenroth and CE Rasmussen
    Reducing Model Bias in Reinforcement Learning
    NIPS Workshop on Learning and Planning from Batch Time Series Data , Whistler, BC, Canada.
    details
  3. R Turner, MP Deisenroth, and CE Rasmussen
    State-Space Inference and Learning with Gaussian Processes
    13th International Conference on Artificial Intelligence and Statistics (AISTATS 2010), Sardinia, Italy.
    details

2009

  1. R Turner, MP Deisenroth, and CE Rasmussen
    System Identification in Gaussian Process Dynamical Systems
    Nonparametric Bayes Workshop at NIPS 2009, Whistler, Canada, December 2009.
    details
  2. MP Deisenroth and CE Rasmussen
    Efficient Reinforcement Learning for Motor Control
    10th International PhD Workshop on Systems and Control, a Young Generation Viewpoint, Hluboka nad Vltavou, Czech Republic, September 2009.
    details
  3. MP Deisenroth, MF Huber, and UD Hanebeck
    Analytic Moment-based Gaussian Process Filtering
    in Proceedings of the 26th International Conference on Machine Learning (ICML 2009), pp. 225–232, Omnipress.
    details
  4. MP Deisenroth and CE Rasmussen
    Bayesian Inference for Efficient Learning in Control
    in Multidisciplinary Symposium on Reinforcement Learning (MSRL), Montreal, Canada, June 2009.
    details
  5. MP Deisenroth, CE Rasmussen, and J Peters
    Gaussian Process Dynamic Programming
    in Neurocomputing, vol. 72, no 7–9, pp. 1508–1524, Elsevier, March 2009.
    details

2008

  1. CE Rasmussen and MP Deisenroth
    Probabilistic Inference for Fast Learning in Control
    chapter in Recent Advances in Reinforcement Learning, Lecture Notes on Computer Science, LNAI series, vol. 5323, pp. 229–242, Springer-Verlag, November 2008.
    details
  2. MP Deisenroth, J Peters, and CE Rasmussen
    Approximate Dynamic Programming with Gaussian Processes
    in Proceedings of the 2008 American Control Conference (ACC 2008), pp. 4480–4485, June 2008, Seattle, WA, USA.
    details
  3. MP Deisenroth, CE Rasmussen, and J Peters
    Model-Based Reinforcement Learning with Continuous States and Actions
    in Proceedings of the European Symposium on Artificial Neural Networks (ESANN 2008), pp. 19–24, April 2008, Bruges, Belgium.
    details

2007

  1. MP Deisenroth, F Weissel, T Ohtsuka, and UD Hanebeck
    Online-Computation Approach to Optimal Control of Noise-Affected Nonlinear Systems with Continuous State and Control Spaces
    Proceedings of the 9th European Control Conference 2007 (ECC 2007), pp. 3664–3671, July 2007, Kos, Greece.
    details

2006

  1. MP Deisenroth, F Weissel, T Ohtsuka, D Brunn, and UD Hanebeck
    Finite-Horizon Optimal State-Feedback Control of Nonlinear Stochastic Systems Based on a Minimum Principle
    Proceedings of the 6th IEEE International Conference on Multisensor Fusion and Integration (MFI 2006), pp. 371–376, September 2006, Heidelberg, Germany.
    details

Technical Reports

  1. MP Deisenroth and CE Rasmussen
    A Practical and Conceptual Framework for Learning in Control
    Department of Computer Science & Engineering, University of Washington, Seattle, WA, USA
    UW-CSE-10-06-01, June 2010
    details

Theses

  1. MP Deisenroth
    Efficient Reinforcement Learning using Gaussian Processes
    PhD Thesis, Karlsruhe Institute of Technology, 2009.
  2. MP Deisenroth
    An Online-Computation Approach to Optimal Finite-Horizon State-Feedback Control of Nonlinear Stochastic Systems
    MSc Thesis, Universität Karlsruhe (TH), 2006.
  3. MP Deisenroth
    Toward Optimal Control of Nonlinear Systems with Continuous State Spaces
    BSc Thesis, Universität Karlsruhe (TH), 2004.

Posters

  1. MP Deisenroth and CE Rasmussen
    PILCO: A Model-based and Data Efficient Approach to Policy Search
    International Conference on Machine Learning, Bellevue, WA, USA, July 2011.
    [pdf]
  2. MP Deisenroth, CE Rasmussen, and D Fox
    Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning
    International Conference on Robotics: Science & Systems, Los Angeles, CA, USA, June 2011
    [pdf]
  3. MP Deisenroth and CE Rasmussen
    Reducing Model Bias in Reinforcement Learning
    NIPS Workshop on Learning and Planning from Batch Time Series Data, Whistler, BC, Canada, December 2010.
    [pdf] [link]
  4. MP Deisenroth and D Fox
    Autonomous Learning in Robotics
    University of Washington, Seattle, USA, November 2010.
  5. MP Deisenroth and CE Rasmussen
    Probabilistic Inference for Fast Learning in Control
    University of Washington, Seattle, USA, November 2010.
  6. L Bo, MP Deisenroth, D Fox, L LeGrand, C Matuszek
    Gambit: Piece Recognition and Visual Servoing
    Open House, Intel Labs Seattle, November 2010.
  7. C Matuszek, R Aimi, L Bo, R Chu, MP Deisenroth, D Fox, M Kung, L LeGrand, B Mayton, and JR Smith
    Gambit: Autonomous Small-Scale Manipulation for Chess
    Open House, Intel Labs Seattle, November 2010.
  8. R Turner, MP Deisenroth, and CE Rasmussen
    State-Space Inference and Learning with Gaussian Processes
    AISTATS 2010, Sardinia, Italy, May 2010.
  9. R Turner, MP Deisenroth, and CE Rasmussen
    System Identification in Gaussian Process Dynamical Systems
    Nonparametric Bayes Workshop at NIPS, Whistler, BC, Canada, December 2009.
  10. MP Deisenroth and CE Rasmussen
    Bayesian Inference for Efficient Learning in Control
    Microsoft Research Summer School, Cambridge, UK, June 2009
    [pdf] [link]
  11. MP Deisenroth and CE Rasmussen
    Bayesian Inference for Efficient Learning in Control
    Multidisciplinary Symposium on Reinforcement Learning, Montreal, Canada, June 2009
    [pdf] [abstract] [link]
  12. MP Deisenroth, MF Huber, and UD Hanebeck
    Analytic Moment-based Gaussian Process Filtering
    International Conference on Machine Learning, Montreal, Canada, June 2009
    [pdf] [paper] [discussion] [link]
  13. MP Deisenroth and CE Rasmussen
    Bayesian Inference for Fast Learning Control
    Cambridge, UK, October 2008
  14. MP Deisenroth, F Doshi, M Lengyel, CE Rasmussen, and Z Ghahramani
    System that Learn to Make Decisions
    HORIZON Seminar: The Thinking Machine, Cambridge, UK, March 2008
    [pdf]
  15. MP Deisenroth, CE Rasmussen, and J Peters
    Dynamic Programming with Gaussian Process Models
    EPSRC Winter School: Mathematics for Data Modelling, Sheffield, UK, January 2008
    [pdf]
Intel Labs Seattle, USA || Machine Learning Group, University of Cambridge, UK || MPI for Biological Cybernetics, Tübingen, Germany || AI@UW || UW Privacy Policy || UW Terms of Use