Conference Proceedings :

A. MANUKYAN, M.A.. OLIVARES-MENDEZ, H. VOOS, M. GEIST, "Real time degradation identification of UAV using machine learning techniques". In International Conference on Unmanned Aircraft Systems (ICUAS'17), 2017.

Regular Papers :

B. PIOT, M. GEIST, O. PIETQUIN, "Bridging the Gap between Imitation Learning and Inverse Reinforcement Learning". In IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2016.

Conference Proceedings :

B. PIOT, M. GEIST, O. PIETQUIN, "Batch Policy Iteration Algorithms for Continuous Domains". In European Workshop on Reinforcement Learning (EWRL), 2016.

J. PÉROLAT, B. PIOT, M. GEIST, B. SCHERRER, O. PIETQUIN, "Softened Approximate Policy Iteration for Markov Games". In International Conference on Machine Learning (ICML), 2016.

L. EL ASRI, B. PIOT, M. GEIST, R. LAROCHE, O. PIETQUIN, "Score-based Inverse Reinforcement Learning". In International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2016), 2016.

Thesis :

M. GEIST, "Contrôle optimal et apprentissage automatique, applications aux interactions homme-machine", Habilitation à Diriger des Recherches, PhD Thesis, Université de Lille 1, 2016.

Miscellaneous :

M. GEIST, B. PIOT, O. PIETQUIN, "Should one minimize the expected Bellman residual or maximize the mean value?", arxiv, 2016.

B. PIOT, M. GEIST, O. PIETQUIN, "Difference of Convex Functions Programming Applied to Control with Expert Data", arxiv, 2016.

Regular Papers :

B. SCHERRER, M. GEIST, "Recherche locale de politique dans un espace convexe". In Revue d'Intelligence Artificielle (RIA), 29(6):685-704, 2015.

M. GEIST, "Soft-max boosting". In Machine Learning, 100(2):305-332, (I discovered after publication that a very similar approach has been published some time ago, see "an iterative method for multi-class cost-sensitive learning" by Abe, Zadrozny and Langford, KDD'04), 2015.

B. SCHERRER, M. GHAVAMZADEH, V. GABILLON, B. LESNER, M. GEIST, "Approximate Modified Policy Iteration and its Application to the Game of Tetris". In Journal of Machine Learning Research, 16:1629-1676, 2015.

Conference Proceedings :

M. LAUFFER, F. GENTY, S. MARGUERON, J.L. COLLETTE, J.C. PIHAN, "Automatic recognition system of aquatic organisms by classical and fluorescence microscopy". In Proceedings of SPIE 9506, 9506(1O):1-7, Prague (République Tchèque), 2015.

S. ROSSIGNOL, "Technique d'assistance par le bruit pour aider l'opérateur de Teager-Kaiser à suivre une composante fréquentielle perturbée par du bruit". In GRETSI, 2015.

B. PIOT, M. GEIST, O. PIETQUIN, "Imitation Learning Applied to Embodied Conversational Agents". In Machine Learning and Interactive Systems (MLIS), 2015.

M. GEIST, "A multiplicative UCB strategy for Gamma rewards". In European Workshop on Reinforcement Learning (EWRL), 2015.

T.. MUNZER, B. PIOT, M. GEIST, O. PIETQUIN, M.. LOPES, " Inverse Reinforcement Learning in Relational Domains". In International Joint Conferences on Artificial Intelligence (IJCAI), (to appear), 2015.

Regular Papers :

H. FREZZA-BUET, "Online Computing of Non-Stationary Distributions Velocity Fields by an Accuracy Controlled Growing Neural Gas". In Neural Networks, 60:203--221, 2014.

M. GEIST, B. SCHERRER, "Off-policy Learning with Eligibility Traces: A Survey". In Journal of Machine Learning Research (JMLR), 15:289-333, 2014.

N. FRESSENGEAS, H. FREZZA-BUET, "Cellular Computing and Least Squares for partial differential problems parallel solving". In Journal of Cellular Auromata, 9(1):1-21, 2014.

Conference Proceedings :

M. LAUFFER, F. GENTY, S. MARGUERON, J.L. COLLETTE, A. LEVEY, Y. HOUZELLE, J.C. PIHAN, "Fluorescence imaging of plant pigments for automatical recognition of aquatic organisms". In Proceedings of the XII Conference on Optical Chemical Sensors and Biosensors:FS-29, Athens (Grèce), 2014.

B. PIOT, M. GEIST, O. PIETQUIN, "Difference of Convex Functions Programming for Reinforcement Learning". In Advances in Neural Information Processing Systems (NIPS 2014), 2014.

B. PIOT, O. PIETQUIN, M. GEIST, "Predicting when to laugh with structured classification". In Annual Conference of the International Speech Communication Association (InterSpeech), 2014.

B. SCHERRER, M. GEIST, "Local Policy Search in a Convex Space and Conservative Policy Iteration as Boosted Policy Search". In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), (to appear), 2014.

B. PIOT, M. GEIST, O. PIETQUIN, "Boosted Bellman Residual Minimization Handling Expert Demonstrations". In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Springer, (to appear), 2014.

J. FIX, "Dynamic formation of self-organizing maps". In 10th workshop on Self-Organizing Maps, WSOM 2014, 2014.

D. BAHEUX, H. FREZZA-BUET, J. FIX, "Towards an effective multi-map self organizing recurrent neuronal network". In Proc. ESANN, 2014.

B. PIOT, M. GEIST, O. PIETQUIN, "Boosted and Reward-regularized Classification for Apprenticeship Learning". In 13th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2014), Paris, France, (accepted, to appear), 2014.

Thesis :

B. KHOUZAM, "Neural Networks as Cellular Computing Models for Temporal Sequence Porcessing", PhD Thesis, Supélec, 2014.

Workshops :

B. PIOT, M. GEIST, O. PIETQUIN, "Méthode de minimisation du résidu de Bellman boostée qui tient compte des démonstrations expertes". In Journées Francophone de Plannification, Décision et Apprentissage (JFPDA), 2014.

B. SCHERRER, M. GEIST, "Quand l'optimalité locale implique une garantie globale : recherche locale de politique dans un espace convexe et algorithme d'itération sur les politiques conservatif vu comme une montée de gradient ". In Journées Francophone de Plannification, Décision et Apprentissage (JFPDA), 2014.

Regular Papers :

J. FIX, "Template based black-box optimization of dynamic neural fields". In Neural Networks, 46:40--49, 2013.

H. FREZZA-BUET, M. GEIST, "A C++ Template-Based Reinforcement Learning Library: Fitting the Code to the Mathematics". In Journal of Machine Learning Research, 14:625 - 628, 2013.

M. GEIST, O. PIETQUIN, "Algorithmic Survey of Parametric Value Function Approximation". In IEEE Transactions on Neural Networks and Learning Systems, 24(6):845 - 867, pdf, 2013.

E. KLEIN, B. PIOT, M. GEIST, O. PIETQUIN, "Classification structurée pour l'apprentissage par renforcement inverse". In Revue d'Intelligence Artificielle, 27(2/2013):155-170, pdf, 2013.

B. KHOUZAM, H. FREZZA-BUET, "Distributed Recurrent Self-Organization for Tracking the State of Non-Stationary Partially Observable Dynamical Systems". In Biologically Inspired Cognitive Architectures, 3:87--104, 2013.

O. PIETQUIN, H. HASTIE, "A survey on metrics for the evaluation of user simulations". In Knowledge Engineering Review, 28(01):59-73, first published as FirstView, 2013.

Conference Proceedings :

L. DAUBIGNEY, M. GEIST, O. PIETQUIN, "Model-free POMDP optimisation of tutoring systems with echo-state networks". In Proceedings of the 14th SIGDial Meeting on Discourse and Dialogue (SIGDial 2013):102-106, Metz (France), 2013.

B. PIOT, M. GEIST, O. PIETQUIN, "Learning from demonstrations: Is it worth estimating a reward function?". In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2013), Blockeel, Hendrik and Kersting, Kristian and Nijssen, Siegfried and Zelezny, Filip, ISBN: 978-3-642-40987-5, Springer, Lecture Notes in Computer Science, 8188:17-32, Prague (Czech Republic) , 2013.

E. KLEIN, B. PIOT, M. GEIST, O. PIETQUIN, "A cascaded supervised learning approach to inverse reinforcement learning". In Proceedings of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD 2013), Blockeel, Hendrik and Kersting, Kristian and Nijssen, Siegfried and Zelezny, Filip, ISBN: 978-3-642-40987-5, Springer, Lecture Notes in Computer Science, 8188:1-16, Prague (Czech Republic) , 2013.

L. DAUBIGNEY, M. GEIST, O. PIETQUIN, "Particle Swarm Optimisation of Spoken Dialogue System Strategies". In Proceedings of the 14th Annual Conference of the International Speech Communication Association (Interspeech 2013), Lyon (France), 2013.

L. EL ASRI, R. LAROCHE, O. PIETQUIN, "Reward Shaping For Statistical Optimisation Of Dialogue Management". In Proceedings of the International Conference on Statistical Language and Speech Processing (SLSP 2013), Dediu, Adrian-Horia and Marti­n-Vide, Carlos and Mitkov, Ruslan and Truthe, Bianca, ISBN: 978-3-642-39592-5, Springer, Lecture Notes in Computer Science , 7978:93-101, Tarragona (Spain), 2013.

O. PIETQUIN, "Inverse Reinforcement Learning for Interactive Systems". In Proceedings of the IJCAI workshop on Machine Learning for Interactive Systems (MLIS 2013), Beijing (China), Invited Speaker, 2013.

L. DAUBIGNEY, M. GEIST, O. PIETQUIN, "Random Projections: a Remedy for Overfitting Issues in Time Series Prediction with Echo State Networks". In Proceedings of the 38th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2013), Vancouver, Canada, to appear, 2013.

R. NIEWIADOMSKI, J. HOFMANN, J. URBAIN, T. PLATT, J. WAGNER, B. PIOT, H. CAKMAK, S. PAMMI, T. BAUR, S. DUPONT, M. GEIST, F. LINGENFELSER, G. MCKEOWN, O. PIETQUIN, W. RUCH, "Laugh-aware virtual agent and its impact on user amusement ". In Proceedings of the Twelfth International Conference on Autonomous Agents and Multiagent Systems (AAMAS2013):619-626, Saint Paul, USA, 2013.

Proceedings :

M. ESKENAZI, M. STRUBE, B. DI EUGENIO, J. WILLIAMS, O. PIETQUIN, "14th annual SIGdial Meeting on Discourse and Dialogue ", 2013.

Technical Reports :

M. GEIST, B. SCHERRER, "Off-policy Learning with Eligibility Traces: A Survey", Supélec - INRIA, 2013.

Patents :

J. OSTER, G. CLIFFORD, O. PIETQUIN, M. GEIST, "Periodic Artifact Reduction from Biomedical Signals", patent WO2013052944, 2013.

Workshops :

B. PIOT, M. GEIST, O. PIETQUIN, "Classification régularisée par la récompense pour l'Apprentissage par Imitation". In Journées Francophones de Plannification, Décision et Apprentissage (JFPDA), Lille (FRANCE), 2013.

M. GEIST, E. KLEIN, B. PIOT, Y. GUERMEUR, O. PIETQUIN, "Around Inverse Reinforcement Learning and Score-based Classification". In 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton (USA), 2013.

B. PIOT, M. GEIST, O. PIETQUIN, "Learning from demonstrations: Is it worth estimating a reward function?". In 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2013), Princeton, USA, 2013.

L. DAUBIGNEY, M. GEIST, O. PIETQUIN, "Optimisation par essaims particulaires de stratégies de dialogue". In Journées Francophones de Plannification, Décision et Apprentissage (JFPDA), 2013.

E. KLEIN, B. PIOT, M. GEIST, O. PIETQUIN, "Apprentissage par renforcement inverse en cascadant classification et régression". In Journées Francophones de Plannification, Décision et Apprentissage (JFPDA), 2013.

B. PIOT, M. GEIST, O. PIETQUIN, "Apprentissage par démonstrations : vaut-il la peine d'estimer une fonction de récompense?". In Journées Francophones de Plannification, Décision et Apprentissage (JFPDA), 2013.