SIGAUD Olivier
Departure date : 08/31/2005
2007
DEGRIS Thomas : Apprentissage par renforcement dans les processus de décision Markoviens factorisés .
1999-2020 Publications
All
Books
Edited books
Journal articles
Book chapters
Conference papers
Thesis
2020
I. Bloch, R. Clouard, M. Revenu, O. Sigaud : “Artifical Intelligence and Pattern Recognition, Vision, Learning ”, chapter in A Guided Tour of Artificial Intelligence Research (P. Marquis, O. Papini, H. Prade, Eds), vol. III, pp. 337-364, (Springer) (2020)
2014
I. Bloch, R. Clouard, M. Revenu, O. Sigaud : “7 : Intelligence artificielle et reconnaissance des formes, vision, apprentissage ”, chapitre de Panorama de l’intelligence artificielle - Ses bases mĂ©thodologiques ses dĂ©veloppements - Volume 3 (P. Marquis, O. Papini, H. Prade, eds.), pp. 1165-1195, (CĂ©paduès) (2014)
I. Bloch, R. Clouard, M. Revenu, O. Sigaud : “Intelligence artificielle et reconnaissance des formes, vision, apprentissage pour la robotique ”, chapter in L'Intelligence Artificielle : Frontières et Applications, Volume 3, sĂ©rie : Panorama de l'Intelligence Artificielle, pp. 30 pp, (Editions CEPADUES), (ISBN: 9782364930438) (2014)
2009
O. Kozlova, O. Sigaud, P.‑H. Wuillemin, Ch. Meyer : “Considering Unseen States as Impossible in Factored Reinforcement Learning ”, European Conference on Machine Learning, vol. 5781, Lecture Notes in Computer Science, Bled, Slovenia, pp. 721-735, (Springer) (2009)
Th. Degris, O. Sigaud, P.‑H. Wuillemin : “Apprentissage par renforcement factorisĂ© pour le comportement de personnages non joueurs ”, Revue des Sciences et Technologies de l'Information - SĂ©rie RIA : Revue d'Intelligence Artificielle, vol. 23 (2-3), pp. 221-251, (Lavoisier) (2009)
2006
Th. Degris, O. Sigaud, P.‑H. Wuillemin : “Chi-square Tests Driven Method for Learning the Structure of Factored MDPs ”, Proceedings of the 22nd conference on Uncertainty in Artificial Intelligence, Massachusetts Institute of Technology, Cambridge, MA, United States, pp. 122-129, (AUAI Press) (2006)
Th. Degris, O. Sigaud, P.‑H. Wuillemin : “Learning the Structure of Factored Markov Decision Processes in Reinforcement Learning Problems ”, Proceedings of the 23rd International Conference on Machine Learning, Pittsburgh, Pennsylvania, United States, pp. 257-264, (ACM) (2006)
Th. Degris, O. Sigaud, P.‑H. Wuillemin : “Apprentissage de la structure des processus de dĂ©cision markoviens factorisĂ©s pour l’apprentissage par renforcement ”, Actes de la confĂ©rence JournĂ©es Francophones sur la Planification, la DĂ©cision et l'Apprentissage pour la Conduite de Systèmes 2006, Toulouse, France, pp. 89-96 (2006)
F. Charpillet, F. Garcia, P. Perny, O. Sigaud : “DĂ©cision et planification dans l’incertain ”, Revue des Sciences et Technologies de l'Information - SĂ©rie RIA : Revue d'Intelligence Artificielle, vol. 20, pp. 432, (Lavoisier) (2006)
F. Flacher, O. Sigaud : “GACS : une approche ascendante pour la coordination spatiale ”, Revue des Sciences et Technologies de l'Information - SĂ©rie RIA : Revue d'Intelligence Artificielle, vol. 20 (1), pp. 7-30, (Lavoisier) (2006)
2005
Th. Gourdin, O. Sigaud : “Towards a Reinforcement Learning Module for Navigation in Video Games ”, ECML 2005 Workshop on Reinforcement Learning in Non-Stationary Environments, Porto, Portugal, pp. 1-12 (2005)
F. Flacher, O. Sigaud : “GACS, an Evolutionary Approach to the Spatial Coordination of Agents ”, AAMAS 2005 - 4th international joint conference on Autonomous agents and multiagent systems, Utrecht, Netherlands, pp. 1109-1110, (ACM Press) (2005)
P. GĂ©rard, J.‑A. Meyer, O. Sigaud : “Combining latent learning with dynamic programming in the modular anticipatory classifier system ”, European Journal of Operational Research, vol. 160 (3), pp. 614-637, (Elsevier) (2005)
S. Landau, O. Sigaud, M. Schoenauer : “ATNoSFERES revisited ”, GECCO 2005 - 7th annual conference on Genetic and Evolutionary Computation Conference,, vol. 2, Washington DC, United States, pp. 1867-1874 (2005)
2004
O. Sigaud : “comportements adaptatifs pour les agents en environnement informatique complexe ”, habilitation, defence 12/10/2004 (2004)
V. LabbĂ©, O. Sigaud, Ph. Codognet : “Anticipation of Periodic Movements in Real Time 3D Environments ”, ABiALS 2004 - 2nd Workshop of Anticipatory Behavior in Adaptive Learning Systems, Los Angeles, CA, United States, pp. 51-61 (2004)
F. Flacher, O. Sigaud : “BASC, a Bottom-up Approach to automated design of Spatial Coordination ”, SAB 2004 - 8th International Conference on Simulation of Adaptive Behavior, Los Angeles, CA, United States, pp. 435-444, (MIT Press) (2004)
S. Landau, O. Sigaud : “A Michigan style architecture for learning finite state controllers: a first step ”, 7th International Workshop on Learning Classifier Systems, Seattle, WA, United States (2004)
Th. Gourdin, O. Sigaud, P.‑H. Wuillemin : “Improving MACS thanks to a comparison with 2TBNs ”, GECCO 2004 - Genetic and Evolutionary Computation Conference, vol. 3103, Lecture Notes in Computer Science, Seattle, WA, United States, pp. 810-823, (Springer) (2004)
Th. Degris, O. Sigaud, S. Wiener, A. Arleo : “Rapid response of head direction cells to reorienting visual cues: A computational model ”, Neurocomputing, vol. 58-60, pp. 675-682, (Elsevier) (2004)
Z. Guessoum, L. Rejeb, O. Sigaud : “Using XCS to build adaptive agents ”, 4th Symposium on Adaptive Agents and Multi-Agent Systems (AAMAS-4), AISB convention, Leeds, United Kingdom, pp. 101-106 (2004)
P. GĂ©rard, O. Sigaud : “Apprentissage par renforcement indirect dans les systèmes de classeurs ”, JEDAI - Journal Ă©lectronique d'intelligence artificielle, vol. 4, pp. 19, (AFIA) (2004)
2003
P. GĂ©rard, O. Sigaud : “Designing Efficient Exploration with MACS: Modules and Function Approximation ”, Genetic and Evolutionary Computation Conference 2003 (GECCO03), vol. 2724, Lecture Notes in Computer Science, Chicago, IL, United States, pp. 1882-1893, (Springer-Verlag) (2003)
O. Sigaud, P. GĂ©rard : “Apprentissage par renforcement indirect dans les systèmes de classeurs ”, Troisièmes JournĂ©es Nationales sur Processus DĂ©cisionnel de Markov et Intelligence Artificielle - PDMIA’03, Caen, France (2003)
Martin V. Butz, O. Sigaud, P. GĂ©rard : “Anticipatory Behavior in Adaptive Learning Systems ”, vol. 2684, Lecture Notes in Computer Science, (Springer) (2003)
Martin V. Butz, O. Sigaud, P. GĂ©rard : “Anticipatory Behavior: Exploiting Knowledge about the Future to Improve Current Behavior ”, chapter in Anticipatory Behavior in Adaptive Learning Systems, vol. 2684, Lecture Notes in Computer Science, pp. 1-10, (Springer) (2003)
F. Flacher, O. Sigaud : “Coordination spatiale Ă©mergente par champs de potentiel ”, Revue des Sciences et Technologies de l'Information - SĂ©rie TSI : Technique et Science Informatiques, vol. 22 (2), pp. 171-195, (Lavoisier) (2003)
Martin V. Butz, O. Sigaud, P. GĂ©rard : “Internal Models and Anticipations in Adaptive Learning Systems ”, chapter in Anticipatory Behavior in Adaptive Learning Systems, vol. 2684, Lecture Notes in Computer Science, pp. 86-109, (Springer) (2003)
2002
P. GĂ©rard, W. Stolzmann, O. Sigaud : “YACS : Yet a new Learning Classifier System using Anticipation. ”, Soft Computing, vol. 6 (3-4), pp. 216-228, (Springer Verlag) (2002)
S. Landau, S. Picault, O. Sigaud, P. GĂ©rard : “Further Comparison between ATNoSFERES and XCSM ”, IWLCS 2002 - 5th International Workshop on Learning Classifier Systems, vol. 2661, Lecture Notes in Computer Science, Granada, Spain, pp. 99-117, (Springer) (2002)
S. Landau, S. Picault, O. Sigaud, P. GĂ©rard : “A Comparison between ATNoSFERES and XCSM ”, GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, New York, United States, pp. 926-933, (Morgan Kaufmann) (2002)
F. Flacher, O. Sigaud : “Spatial Coordination through Social Potential Fields and Genetic Algorithms ”, 7th International Conference on Simulation of Adaptive Behavior, Edimburg, United Kingdom, pp. 389-390, (The MIT Press) (2002)
O. Sigaud, F. Flacher : “Vers une approche dynamique de la sĂ©lection de l’action ”, chapitre de Approche dynamique de la cognition artificielle, pp. 163-178, (Hermès) (2002)
2001
P. GĂ©rard, O. Sigaud : “Adding a Generalization Mechanism to YACS ”, GECCO 2001 - 3rd Annual Conference on Genetic and Evolutionary Computation, San Francisco, CA, United States, pp. 951-957, (Morgan Kaufmann) (2001)
P. GĂ©rard, O. Sigaud : “GĂ©nĂ©ralisation et apprentissage latent dans les systèmes de classeurs ”, Extraction de connaissances et apprentissage, vol. 1 (3), pp. 87-114 (2001)
2000
O. Sigaud, P. GĂ©rard : “Using Classifier Systems as Adaptive Expert Systems for Control ”, Advances in Learning Classifier Systems, vol. 1996, Lecture Notes in Computer Science, Paris, France, pp. 138-157, (Springer-Verlag) (2000)
P. GĂ©rard, O. Sigaud : “YACS : Combining Anticipation and Dynamic Programming in CLassifier Systems ”, IWLCS 2000 - 3rd International Workshop on Learning Classifier Systems, vol. 1996, Lecture Notes in Computer Science, Paris, France, pp. 52-69, (Springer-Verlag) (2000)
O. Sigaud, P. GĂ©rard : “The use of roles in a multiagent adaptive simulation ”, 14th European Conference in Artificial Intelligence, Workshop on Balancing reactivity and Social Deliberation in Multiagent Systems, Berlin, Germany (2000)
O. Sigaud, P. GĂ©rard : “Being Reactive by Exchanging Roles: an Empirical Study ”, chapter in Balancing reactivity and Social Deliberation in Multiagent Systems, vol. 2103, Lecture Notes in Computer Science, pp. 150-172, (Springer-Verlag) (2000)
1999