Sébastien Jodogne

Under the supervision of Prof. Justus H. Piater, my PhD was focused on the development of Reinforcement Learning algorithms that are able to tackle visual control problems. This topic lies on the border between Computer Vision and Machine Learning.

My BibTeX file.

Doctoral dissertation

• S. Jodogne. Closed-Loop Learning of Visual Control Policies. PhD thesis, University of Liège, December 2006.

International journal papers

• J. Piater, S. Jodogne, R. Detry, D. Kraft, N. Krüger, O. Kroemer, and J. Peters. Learning visual representations for perception-action systems. International Journal of Robotics Research, 2010. Accepted for publication.

• C. Briquet, X. Dalem, S. Jodogne, and P.A. de Marneffe. P2P file sharing for P2P computing. Multiagent and Grid Systems, 5(2), 2009.

• S. Jodogne and J.H. Piater. Closed-loop learning of visual control policies. Journal of Artificial Intelligence Research, 28:349–391, March 2007.

• B. Boigelot, S. Jodogne, and P. Wolper. An effective decision procedure for linear arithmetic with integer and real variables. ACM Transactions on Computational Logic (TOCL), 6(3):614–633, July 2005.

International conferences and workshops

• J. Piater, S. Jodogne, R. Detry, D. Kraft, D. Krüger, O. Kroemer, and J. Peters. Learning visual representations for interactive systems. In Proc. of the 14th International Symposium on Robotics Research, 2009. Invited paper.

• C. Briquet, X. Dalem, S. Jodogne, and P.A. de Marneffe. Scheduling data-intensive bags of tasks in P2P grids with BitTorrent-enabled data distribution. In Proc. UPGRADE-CN'07, HPDC Workshops, Monterey Bay (CA, USA), June 2007.

• S. Jodogne, C. Briquet, and J.H. Piater. Approximate policy iteration for closed-loop learning of visual tasks. In Proc. of the 17th European Conference on Machine Learning (ECML), volume 4212 of Lecture Notes in Computer Science, pages 222–233. Springer Verlag, September 2006.

• S. Jodogne and J.H. Piater. Task-driven discretization of the joint space of visual percepts and continuous actions. In Proc. of the 17th European Conference on Machine Learning (ECML), volume 4212 of Lecture Notes in Computer Science, pages 210–221. Springer Verlag, September 2006.

• O. Barnich, S. Jodogne, and M. Van Droogenbroeck. Robust analysis of silhouettes by morphological size distributions. In Advanced Concepts for Intelligent Vision Systems (ACIVS 2006), volume 4179 of Lecture Notes in Computer Science, pages 734–745. Springer Verlag, September 2006.

• S. Jodogne and J.H. Piater. Learning, then compacting visual policies (extended abstract). In Proc. of the 7th European Workshop on Reinforcement Learning (EWRL), pages 8–10, Napoli (Italy), October 2005.

• S. Jodogne and J.H. Piater. Interactive learning of mappings from visual percepts to actions. In L. De Raedt and S. Wrobel, editors, Proc. of the 22nd International Conference on Machine Learning (ICML), pages 393–400, Bonn (Germany), August 2005. ACM.

• S. Jodogne, F. Scalzo, and J.H. Piater. Task-driven learning of spatial combinations of visual features. In Proc. of the IEEE Workshop on Learning in Computer Vision and Pattern Recognition, San Diego (CA, USA), June 2005. IEEE.

• S. Jodogne and J.H. Piater. Reinforcement learning of perceptual classes using Q-learning updates. In M.H. Hamza, editor, Proc. of the 23rd IASTED International Multi-Conference on Artificial Intelligence and Applications, pages 445–450, Innsbruck (Austria), February 2005. Acta Press.

• S. Jodogne and J.H. Piater. Interactive selection of visual features through reinforcement learning. In M. Bramer, F. Coenen, and T. Allen, editors, Proc. of the 24th SGAI Internal Conference on Innovative Techniques and Applications of Artificial Intelligence, volume 21 of Research and Development in Intelligent Systems, pages 285–298, Cambridge (UK), December 2004. Springer-Verlag.

• B. Boigelot, S. Jodogne, and F. Herbreteau. Hybrid acceleration using real vector automata. In Proc. of the 15th International Conference on Computer Aided Verification, volume 2725 of Lecture Notes in Computer Science, pages 193–205, Boulder (CO, USA), July 2003. Springer-Verlag.

• B. Boigelot, S. Jodogne, and P. Wolper. On the use of weak automata for deciding linear arithmetic with integer and real variables. In Proc. International Joint Conference on Automated Reasoning (IJCAR), volume 2083 of Lecture Notes in Computer Science, pages 611–625, Sienna (Italy), June 2001. Springer-Verlag.

National journal papers

• S. Jodogne and J.H. Piater. Controlling an agent by focusing its attention on interactively selected patterns. Belgian Journal of Electronics and Communications, special issue: URSI Forum 2004, 1:14–16, 2005.

National conferences and workshops

• S. Jodogne and J.H. Piater. Apprentissage interactif de liaisons directes entre perceptions visuelles et actions. In Actes du Congrès ORASIS, Fournols (France), May 2005.

• S. Jodogne. Automata-based representations for the verification of hybrid systems. In Proc. Summer School Modelling and Verification of Parallel Processes (MOVEP), pages 320–325, Nantes (France), June 2002.

Unpublished

• S. Jodogne. Montefiore image database, 2005.

• S. Jodogne. Représentation à états finis d'ensembles de réels, May 2001. Master's thesis, University of Liège.