Emmanuel Rachelson

68 papers A* 9A 5B 2C 2Misc 2Journal 38Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization. AAAI Paul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson
2025	J	`jnl`	A Markov Decision Process for Variable Selection in Branch & Bound. CoRR Paul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson
2025	J	`jnl`	Influence branching for learning to solve mixed-integer programs online. CoRR Paul Strang, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum, Emmanuel Rachelson
2025	J	`jnl`	Learning Abstract World Models with a Group-Structured Latent Space. CoRR Thomas Delliaux, Nguyen-Khanh Vu, Vincent François-Lavet, Elise van der Pol, Emmanuel Rachelson
2025	—	`conf`	Learning to Repair Infeasible LION (2) Mehdi Zouitine, Ahmad Berjaoui, Agnès Lagnoux, Clément Pellegrini, Emmanuel Rachelson
2025	J	`jnl`	On the integration of Dantzig-Wolfe and Fenchel decompositions via directional normalizations. EURO J. Comput. Optim. François Lamothe, Alain Haït, Emmanuel Rachelson, Claudio Contardo, Bernard Gendron
2025	J	`jnl`	Planning in Branch-and-Bound: Model-Based Reinforcement Learning for Exact Combinatorial Optimization. CoRR Paul Strang, Zacharie Alès, Côme Bissuel, Safia Kedad-Sidhoum, Emmanuel Rachelson
2024	J	`jnl`	Bootstrapping Expectiles in Reinforcement Learning. CoRR Pierre Clavier, Emmanuel Rachelson, Erwan Le Pennec, Matthieu Geist
2024	J	`jnl`	Disentanglement by Cyclic Reconstruction. IEEE Trans. Neural Networks Learn. Syst. David Bertoin, Emmanuel Rachelson
2024	J	`jnl`	Exploration by Learning Diverse Skills through Successor State Measures. CoRR Paul-Antoine Le Tolguenec, Yann Besse, Florent Teichteil-Königsbuch, Dennis G. Wilson, Emmanuel Rachelson
2024	A*	`conf`	Exploration by Learning Diverse Skills through Successor State Representations. NeurIPS Paul-Antoine Le Tolguenec, Yann Besse, Florent Teichteil-Königsbuch, Dennis Wilson, Emmanuel Rachelson
2024	J	`jnl`	Exploration by Running Away from the Past. CoRR Paul-Antoine Le Tolguenec, Yann Besse, Florent Teichteil-Königsbuch, Dennis G. Wilson, Emmanuel Rachelson
2024	A	`conf`	Exploration-Driven Reinforcement Learning for Avionic System Fault Detection (Experience Paper). ISSTA Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Florent Teichteil-Königsbuch, Nicolas Schneider, Hélène Waeselynck, Dennis Wilson
2024	B	`conf`	Genetic Drift Regularization: On Preventing Actor Injection from Breaking Evolution Strategies. CEC Paul Templier, Emmanuel Rachelson, Antoine Cully, Dennis G. Wilson
2024	J	`jnl`	Genetic Drift Regularization: on preventing Actor Injection from breaking Evolution Strategies. CoRR Paul Templier, Emmanuel Rachelson, Antoine Cully, Dennis G. Wilson
2024	—	`conf`	Learning Heuristics for Combinatorial Optimization Problems on K-Partite Hypergraphs. CPAIOR (2) Mehdi Zouitine, Ahmad Berjaoui, Agnès Lagnoux, Clément Pellegrini, Emmanuel Rachelson
2024	J	`jnl`	Learning State Reachability as a Graph in Translation Invariant Goal-based Reinforcement Learning Tasks. Trans. Mach. Learn. Res. Hedwin Bonnavaud, Alexandre Albore, Emmanuel Rachelson
2024	A	`conf`	Quality with Just Enough Diversity in Evolutionary Policy Search. GECCO Paul Templier, Luca Grillotti, Emmanuel Rachelson, Dennis Wilson, Antoine Cully
2024	J	`jnl`	Quality with Just Enough Diversity in Evolutionary Policy Search. CoRR Paul Templier, Luca Grillotti, Emmanuel Rachelson, Dennis G. Wilson, Antoine Cully
2024	J	`jnl`	RRLS : Robust Reinforcement Learning Suite. CoRR Adil Zouitine, David Bertoin, Pierre Clavier, Matthieu Geist, Emmanuel Rachelson
2024	J	`jnl`	Solving robust MDPs as a sequence of static RL problems. CoRR Adil Zouitine, Matthieu Geist, Emmanuel Rachelson
2024	—	`conf`	Summary of "Curiosity creates Diversity in Policy Search". GECCO Companion Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Dennis Wilson
2024	J	`jnl`	The Overfocusing Bias of Convolutional Neural Networks: A Saliency-Guided Regularization Approach. CoRR David Bertoin, Eduardo Hugo Sanchez, Mehdi Zouitine, Emmanuel Rachelson
2024	A*	`conf`	Time-Constrained Robust MDPs. NeurIPS Adil Zouitine, David Bertoin, Pierre Clavier, Matthieu Geist, Emmanuel Rachelson
2024	J	`jnl`	Time-Constrained Robust MDPs. CoRR Adil Zouitine, David Bertoin, Pierre Clavier, Matthieu Geist, Emmanuel Rachelson
2023	J	`jnl`	Curiosity Creates Diversity in Policy Search. ACM Trans. Evol. Learn. Optim. Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Dennis G. Wilson
2023	J	`jnl`	Dynamic unsplittable flows with path-change penalties: New formulations and solution schemes for large instances. Comput. Oper. Res. François Lamothe, Emmanuel Rachelson, Alain Haït, Cédric Baudoin, Jean-Baptiste Dupe
2023	J	`jnl`	Randomized rounding algorithms for large scale unsplittable flow problems. CoRR François Lamothe, Emmanuel Rachelson, Alain Haït, Cédric Baudoin, Jean-Baptiste Dupe
2022	J	`jnl`	Curiosity creates Diversity in Policy Search. CoRR Paul-Antoine Le Tolguenec, Emmanuel Rachelson, Yann Besse, Dennis G. Wilson
2022	A	`conf`	LUCIE: an evaluation and selection method for stochastic problems. GECCO Erwan Lecarpentier, Paul Templier, Emmanuel Rachelson, Dennis G. Wilson
2022	A*	`conf`	Large Batch Experience Replay. ICML Thibault Lahire, Matthieu Geist, Emmanuel Rachelson
2022	A*	`conf`	Local Feature Swapping for Generalization in Reinforcement Learning. ICLR David Bertoin, Emmanuel Rachelson
2022	J	`jnl`	Local Feature Swapping for Generalization in Reinforcement Learning. CoRR David Bertoin, Emmanuel Rachelson
2022	A*	`conf`	Look where you look! Saliency-guided Q-networks for generalization in visual Reinforcement Learning. NeurIPS David Bertoin, Adil Zouitine, Mehdi Zouitine, Emmanuel Rachelson
2022	J	`jnl`	Look where you look! Saliency-guided Q-networks for visual RL tasks. CoRR David Bertoin, Adil Zouitine, Mehdi Zouitine, Emmanuel Rachelson
2022	—	`conf`	Neural Distillation as a State Representation Bottleneck in Reinforcement Learning. CoLLAs Valentin Guillet, Dennis George Wilson, Emmanuel Rachelson
2022	J	`jnl`	Neural Distillation as a State Representation Bottleneck in Reinforcement Learning. CoRR Valentin Guillet, Dennis G. Wilson, Carlos Aguilar Melchor, Emmanuel Rachelson
2022	—	`conf`	On Neural Consolidation for Transfer in Reinforcement Learning. SSCI Valentin Guillet, Dennis Wilson, Carlos Aguilar Melchor, Emmanuel Rachelson
2022	J	`jnl`	On Neural Consolidation for Transfer in Reinforcement Learning. CoRR Valentin Guillet, Dennis G. Wilson, Carlos Aguilar Melchor, Emmanuel Rachelson
2022	—	`conf`	When, where, and how to add new neurons to ANNs. AutoML Kaitlin Maile, Emmanuel Rachelson, Hervé Luga, Dennis George Wilson
2022	J	`jnl`	When, where, and how to add new neurons to ANNs. CoRR Kaitlin Maile, Emmanuel Rachelson, Hervé Luga, Dennis G. Wilson
2021	A	`conf`	A geometric encoding for neural network evolution. GECCO Paul Templier, Emmanuel Rachelson, Dennis G. Wilson
2021	J	`jnl`	Disentanglement by Cyclic Reconstruction. CoRR David Bertoin, Emmanuel Rachelson
2021	J	`jnl`	Large Batch Experience Replay. CoRR Thibault Lahire, Matthieu Geist, Emmanuel Rachelson
2021	A*	`conf`	Lipschitz Lifelong Reinforcement Learning. AAAI Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman
2021	J	`jnl`	Randomized rounding algorithms for large scale unsplittable flow problems. J. Heuristics François Lamothe, Emmanuel Rachelson, Alain Haït, Cédric Baudoin, Jean-Baptiste Dupe
2021	J	`jnl`	The aircraft runway scheduling problem: A survey. Comput. Oper. Res. Sana Ikli, Catherine Mancel, Marcel Mongeau, Xavier Olive, Emmanuel Rachelson
2020	J	`jnl`	Learning to handle parameter perturbations in Combinatorial Optimization: An application to facility location. EURO J. Transp. Logist. Andrea Lodi, Luca Mossina, Emmanuel Rachelson
2020	J	`jnl`	Lipschitz Lifelong Reinforcement Learning. CoRR Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman
2019	J	`jnl`	A Reinforcement Learning Perspective on the Optimal Control of Mutation Probabilities for the (1+1) Evolutionary Algorithm: First Results on the OneMax Problem. CoRR Luca Mossina, Emmanuel Rachelson, Daniel Delahaye
2019	J	`jnl`	Learning to Handle Parameter Perturbations in Combinatorial Optimization: an Application to Facility Location. CoRR Andrea Lodi, Luca Mossina, Emmanuel Rachelson
2019	C	`conf`	Multi-label Classification for the Generation of Sub-problems in Time-constrained Combinatorial Optimization. ICORES Luca Mossina, Emmanuel Rachelson, Daniel Delahaye
2019	J	`jnl`	Non-Stationary Markov Decision Processes a Worst-Case Approach using Model-Based Reinforcement Learning. CoRR Erwan Lecarpentier, Emmanuel Rachelson
2019	A*	`conf`	Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning. NeurIPS Erwan Lecarpentier, Emmanuel Rachelson
2018	A*	`conf`	Open Loop Execution of Tree-Search Algorithms. IJCAI Erwan Lecarpentier, Guillaume Infantes, Charles Lesire, Emmanuel Rachelson
2018	—	`conf`	Open Loop Execution of Tree-Search Algorithms. JFPDA Erwan Lecarpentier, Guillaume Infantes, Charles Lesire, Emmanuel Rachelson
2018	J	`jnl`	Open Loop Execution of Tree-Search Algorithms. CoRR Erwan Lecarpentier, Guillaume Infantes, Charles Lesire, Emmanuel Rachelson
2017	J	`jnl`	Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring. CoRR Erwan Lecarpentier, Sebastian Rapp, Marc Melo, Emmanuel Rachelson
2017	J	`jnl`	Naive Bayes Classification for Subset Selection. CoRR Luca Mossina, Emmanuel Rachelson
2016	—	`conf`	Approximate Inference in Related Multi-output Gaussian Process Regression. ICPRAM (Revised Selected Papers) Ankit Chiplunkar, Emmanuel Rachelson, Michele Colombo, Joseph Morlier
2016	C	`conf`	Sparse Physics-based Gaussian Process for Multi-output Regression using Variational Inference. ICPRAM Ankit Chiplunkar, Emmanuel Rachelson, Michele Colombo, Joseph Morlier
2014	J	`jnl`	Formal Detection of Attentional Tunneling in Human Operator-Automation Interactions. IEEE Trans. Hum. Mach. Syst. Nicolas Regis, Frédéric Dehais, Emmanuel Rachelson, Charles Thooris, Sergio Pizziol, Mickaël Causse, Catherine Tessier
2011	—	`conf`	Optimal Sample Selection for Batch-mode Reinforcement Learning. ICAART (1) Emmanuel Rachelson, François Schnitzler, Louis Wehenkel, Damien Ernst
2010	—	`conf`	Combining Mixed Integer Programming and Supervised Learning for Fast Re-planning. ICTAI (2) Emmanuel Rachelson, Ala Ben Abbes, Sebastien Diemer
2010	Misc	`conf`	On the locality of action domination in sequential decision making. ISAIM Emmanuel Rachelson, Michail G. Lagoudakis
2009	B	`conf`	TiMDPpoly: An Improved Method for Solving Time-Dependent MDPs. ICTAI Emmanuel Rachelson, Patrick Fabiani, Frédérick Garçia
2008	A	`conf`	A Simulation-based Approach for Solving Generalized Semi-Markov Decision Processes. ECAI Emmanuel Rachelson, Gauthier Quesnel, Frédérick Garçia, Patrick Fabiani
2008	Misc	`conf`	Extending the Bellman equation for MDPs to continuous actions and cont. time in the discounted case. ISAIM Emmanuel Rachelson, Frédérick Garçia, Patrick Fabiani