Raphaël Boige, Amine Boumaza, BS — AlphaBeta is not as good as you think: a simple class of synthetic games for a better analysis of deterministic game-solving algorithms — The Thirty-ninth Annual Conference on Neural Information Processing Systems [article]

Nino Vieillard, Tadashi Kozuno, BS, Olivier Pietquin, Rémi Munos, Matthieu Geist — Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning — NeurIPS - 34th Conference on Neural Information Processing Systems [article]

BS — Simulations de carrières et retraites à points dans 3 cadres macro-économiques: modèle du gouvernement Philippe (âge-pivot bloqué), modèle du gouvernement Philippe corrigé (âge-pivot glissant), modèle Destinie2 (avec revalorisation de la fonction publique) — [article]

Nino Vieillard, BS, Olivier Pietquin, Matthieu Geist — Momentum in Reinforcement Learning — AISTATS 2020 - 23rd International Conference on Artificial Intelligence and Statistics [article]

Romain Postoyan, Mathieu Granzotto, Lucian Buşoniu, BS, Dragan Nešić, Jamal Daafouz — Stability guarantees for nonlinear discrete-time systems controlled by approximate value iteration — 58th IEEE Conference on Decision and Control, CDC 2019 [article]

Yonathan Efroni, Gal Dalal, BS, Shie Mannor — How to Combine Tree-Search Methods in Reinforcement Learning — AAAI 19 - Thirty-Third AAAI Conference on Artificial Intelligence [article]

Matthieu Geist, BS, Olivier Pietquin — A Theory of Regularized Markov Decision Processes — ICML 2019 - Thirty-sixth International Conference on Machine Learning [article]

Yonathan Efroni, Gal Dalal, BS, Shie Mannor — Beyond the one-step greedy approach in reinforcement learning — ICML 2018 - 35th International Conference on Machine Learning [article]

Matthieu Geist, BS — Anderson acceleration for reinforcement learning — EWRL 2018 - 4th European workshop on Reinforcement Learning [article]

Yonathan Efroni, Gal Dalal, BS, Shie Mannor — Multiple-step greedy policies in online and approximate reinforcement learning — NeurIPS 2018 - Thirty-second Conference on Neural Information Processing Systems [article]

Yonathan Efroni, Gal Dalal, BS, Shie Mannor — Convergence of Online and Approximate Multiple-Step Lookahead Policy Iteration — EWRL 2018 - 14th European workshop on Reinforcement Learning [article]

BS — Improved and generalized upper bounds on the complexity of policy iteration — Mathematics of Operations Research [article]

Julien Pérolat, Bilal Piot, Matthieu Geist, BS, Olivier Pietquin — Softened approximate policy iteration for Markov games — ICML 2016 - 33rd International Conference on Machine Learning [article]

Julien Pérolat, Bilal Piot, BS, Olivier Pietquin — On the Use of Non-Stationary Strategies for Solving Two-Player Zero-Sum Markov Games — 19th International Conference on Artificial Intelligence and Statistics (AISTATS 2016) [article]

BS — Contributions algorithmiques au contrôle optimal stochastique à temps discret et horizon infini — Habilitation à diriger des recherches, Université de Lorraine [article]

Boris Lesner, BS — Non-stationary approximate modified policy iteration — ICML 2015 [article]

BS, Matthieu Geist — Recherche locale de politique dans un espace convexe — Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle [article]

BS, Mohammad Ghavamzadeh, Victor Gabillon, Boris Lesner, Matthieu Geist — Approximate modified policy iteration and its application to the game of Tetris — Journal of Machine Learning Research [article]

Julien Perolat, BS, Bilal Piot, Olivier Pietquin — Approximate dynamic programming for two-player zero-sum Markov games — International Conference on Machine Learning (ICML 2015) [article]

Manel Tagorti, BS — On the rate of convergence and error bounds for LSTD(λ) — ICML 2015 [article]

BS, Matthieu 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 fonctionnel — 9èmes Journées Francophones de Planification, Décision et Apprentissage (JFPDA'14) [article]

BS, Matthieu Geist — Local Policy Search in a Convex Space and Conservative Policy Iteration as Boosted Policy Search — ECML [article]

BS — Approximate Policy Iteration Schemes: A Comparison — ICML - 31st International Conference on Machine Learning - 2014 [article]

Matthieu Geist, BS — Off-policy Learning with Eligibility Traces: A Survey — Journal of Machine Learning Research [article]

Eugene A. Feinberg, Jefferson Huang, BS — Modified policy iteration algorithms are not strongly polynomial for discounted dynamic programming — Operations Research Letters [article]

Manel Tagorti, BS — Vitesse de convergence et borne d'erreur pour l'algorithme LSTD(λ) — JFPDA - 9èmes Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes [article]

BS — Une étude comparative de quelques schémas d'approximation de type iterations sur les politiques — [article]

BS — On the Performance Bounds of some Policy Search Dynamic Programming Algorithms — [article]

Alain Dutech, BS, Christophe Thiéry — La carotte et le bâton… et Tetris — Images des mathématiques [article]

BS — Quelques majorants de la complexité d'itérations sur les politiques — JFPDA - 8èmes Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes - 2013 [article]

BS — Improved and Generalized Upper Bounds on the Complexity of Policy Iteration — Neural Information Processing Systems (NIPS) 2013 [article]

Matthieu Geist, BS — Off-policy Learning with Eligibility Traces: A Survey — [article]

Victor Gabillon, Mohammad Ghavamzadeh, BS — Approximate Dynamic Programming Finally Performs Well in the Game of Tetris — Neural Information Processing Systems (NIPS) 2013 [article]

BS, Matthieu Geist — Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee — [article]

BS — Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris — Journal of Machine Learning Research [article]

Manel Tagorti, BS, Olivier Buffet, Joerg Hoffmann — Abstraction Pathologies In Markov Decision Processes — ICAPS'13 workshop on Heuristics and Search for Domain-independent Planning (HSDIP) [article]

BS, Boris Lesner — Sur l'utilisation de politiques non-stationnaires pour les processus de décision Markoviens à horizon infini — JFPDA - 8èmes Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes - 2013 [article]

Boris Lesner, BS — Tight Performance Bounds for Approximate Modified Policy Iteration with Non-Stationary Policies — [article]

Matthieu Geist, BS, Alessandro Lazaric, Mohammad Ghavamzadeh — Un sélecteur de Dantzig pour l'apprentissage par différences temporelles — Journées Francophones sur la planification, la décision et l'apprentissage pour le contrôle des systèmes - JFPDA 2012 [article]

BS — On the Use of Non-Stationary Policies for Infinite-Horizon Discounted Markov Decision Processes — [article]

BS, Victor Gabillon, Mohammad Ghavamzadeh, Matthieu Geist — Approximations de l'Algorithme Itérations sur les Politiques Modifié — Journées Francophones sur la planification, la décision et l'apprentissage pour le contrôle des systèmes - JFPDA 2012 [article]

BS, Boris Lesner — On the Use of Non-Stationary Policies for Stationary Infinite-Horizon Markov Decision Processes — NIPS 2012 - Neural Information Processing Systems [article]

BS, Mohammad Ghavamzadeh, Victor Gabillon, Matthieu Geist — Approximate Modified Policy Iteration — 29th International Conference on Machine Learning - ICML 2012 [article]

Matthieu Geist, BS, Alessandro Lazaric, Mohammad Ghavamzadeh — A Dantzig Selector Approach to Temporal Difference Learning — ICML-12 [article]

Matthieu Geist, BS — l1-penalized projected Bellman residual — European Wrokshop on Reinforcement Learning (EWRL 11) [article]

BS, Matthieu Geist — Recursive Least-Squares Learning with Eligibility Traces — European Wrokshop on Reinforcement Learning (EWRL 11) [article]

Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh, BS — Classification-based Policy Iteration with a Critic — International Conference on Machine Learning (ICML) [article]

BS — Performance Bounds for Lambda Policy Iteration and Application to the Game of Tetris — [article]

BS, Matthieu Geist — Moindres carrés récursifs pour l'évaluation off-policy d'une politique avec traces d'éligibilité — 6ème Journées Francophones de Planification, Décision et Apprentissage pour la conduite de systèmes - JFPDA 2011 [article]

Victor Gabillon, Alessandro Lazaric, Mohammad Ghavamzadeh, BS — Classification-based Policy Iteration with a Critic — [article]

Christophe Thiery, BS — Least-Squares λ Policy Iteration: Bias-Variance Trade-off in Control Problems — International Conference on Machine Learning [article]

BS — Should one compute the Temporal Difference fix point or minimize the Bellman Residual? The unified oblique projection view — 27th International Conference on Machine Learning - ICML 2010 [article]

Christophe Thiery, BS — Least-Squares λ Policy Iteration : optimisme et compromis biais-variance pour le contrôle optimal — Journées Francophones de Planification, Décision et Apprentissage pour la conduite de systèmes [article]

Alain Dutech, BS — Partially Observable Markov Decision Processes — ISTE Ltd and John Wiley & Sons Inc [article]

BS, Christophe Thiery — Performance bound for Approximate Optimistic Policy Iteration — [article]

Christophe Thiery, BS — Improvements on Learning Tetris with Cross Entropy — International Computer Games Association Journal [article]

Christophe Thiery, BS — Une approche modifiée de Lambda-Policy Iteration — Journées Francophones Planification Décision Apprentissage [article]

Christophe Thiery, BS — Construction d'un joueur artificiel pour Tetris — Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle [article]

Christophe Thiery, BS — Building Controllers for Tetris — International Computer Games Association Journal [article]

Marek Petrik, BS — Biasing Approximate Dynamic Programming with a Lower Discount Factor — Twenty-Second Annual Conference on Neural Information Processing Systems -NIPS 2008 [article]

Bernard Girau, Amine Boumaza, BS, Cesar Torres-Huitzil — Block-synchronous harmonic control for scalable trajectory planning — I-Tech Publications [article]

Alain Dutech, BS — Processus décisionnels de Markov partiellement observables — Lavoisier - Hermes Science Publications [article]

Amine Boumaza, BS — Analyse d'un algorithme d'intelligence en essaim pour le fourragement — Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle [article]

BS, Shie Mannor — Error Reducing Sampling in Reinforcement Learning — NIPS-08 Workshop on Model Uncertainty and Risk in Reinforcement Learning [article]

Cesar Torres-Huitzil, Bernard Girau, Amine Boumaza, BS — Embedded harmonic control for trajectory planning in large environments — International Conference on ReConFigurable Computing and FPGAs - ReConFig 08 [article]

Amine Boumaza, BS — Optimal control subsumes harmonic control — IEEE International Conference on Robotics and Automation - ICRA 07 [article]

Amine Boumaza, BS — Convergence and Rate of Convergence of a Foraging Ant Model — IEEE Congress on Evolutionary Computation - IEEE CEC 2007 [article]

Amine Boumaza, BS — Convergence and rate of convergence of a simple ant model — International Conference on Autonomous Agents and Multiagent Systems - AAMAS'07 [article]

BS — Une condition suffisante pour l'implémentation connexionniste asynchrone — 1ère Conférence Francophone Neurosciences Computationnelles - NeuroComp [article]

Amine Boumaza, BS — Optimal control subsumes harmonic control — [article]

BS — Asynchronous Neurocomputing for optimal control and reinforcement learning with large state spaces — Neurocomputing [article]

Amine Boumaza, BS — Navigation, fonctions harmoniques et contrôle optimal stochastique — Cinquièmes Journées Nationales sur Processus Décisionnel de Markov et Intelligence Artificielle - PDMIA 2005 [article]

BS — Approche connexionniste du contrôle optimal — JEDAI - Journal électronique d'intelligence artificielle [article]

BS, Shie Mannor — Error reducing sampling in reinforcement learning — [article]

BS — Modular self-organization — [article]

BS — Parallel asynchronous distributed computations of optimal control in large state space Markov Decision Processes — 11th European Symposium on Artificial Neural Networks - ESANN'03 [article]

BS — Apprentissage de représentation et auto-organisation modulaire pour un agent autonome — Thèse de l'Université Henri Poincaré - Nancy 1 [article]

Iadine Chadès, BS, François Charpillet — Planning Cooperative Homogeneous Multiagent System Using Markov Decision Processes — 5th International Conference on Enterprise Information Systems - ICEIS 2003 [article]

BS — Modular self-organization for a long-living autonomous agent — Eighteenth International Joint Conference on Artificial Intelligence - IJCAI'03 [article]

BS — A connectionist architecture that adpats its representation to complex tasks — International Joint Conference on Neural Networks - IJCNN 2002 [article]

BS, François Charpillet — Cooperative Co-learning: A Model-based Approach for Solving Multi Agent Reinforcement Problems — 14th IEEE International Conference on Tools with Artificial Intelligence - ICTAI 2002 [article]

Iadine Chadès, BS, François Charpillet — A Heuristic Approach for Solving Decentralized-POMDP : Assessment on the Pursuit Problem — ACM Symposium on Applied Computing - SAC'2002 [article]

BS, François Charpillet — Coevolutive Planning In Markov Decision Processes — First International Joint Conference on Autonomous Agents and Multiagent Systems - AAMAS 2002 [article]

Alain Dutech, BS — Learning to use contextual information for solving POMDP — European Workshop on Reinforcement Learning - EWRL-5 [article]

BS — Auto-organisation modulaire d'une architecture intelligente — Valgo numéro 01-02, La revue en ligne de l'Association des Connexionnistes en THèse [article]

BS, Frédéric Alexandre, François Charpillet, Stéphane Vialle — Modélisation stochastique d'une population de neurones, méta-apprentissage dans un problème de classification — Neurosciences et sciences de l'ingénieur [article]