Publications

Article

Lamothe, François and Rachelson, Emmanuel and Haït, Alain and Baudoin, Cedric and Dupé, Jean-Baptiste. Randomized rounding algorithms for large scale unsplittable flow problems. (2021) Journal of Heuristics, 27 (6). 1081-1110. ISSN 1381-1231

Ikli, Sana and Mancel, Catherine and Mongeau, Marcel and Olive, Xavier and Rachelson, Emmanuel. The aircraft runway scheduling problem: A survey. (2021) Computers and Operations Research, 132. 105336. ISSN 0305-0548

Lodi, Andrea and Mossina, Luca and Rachelson, Emmanuel. Learning to handle parameter perturbations in Combinatorial Optimization: An application to facility location. (2020) EURO Journal on Transportation and Logistics, 9 (4). 100023. ISSN 21924376

Mossina, Luca and Rachelson, Emmanuel and Delahaye, Daniel. A Reinforcement Learning Perspective on the Optimal Control of Mutation Probabilities for the (1+1) Evolutionary Algorithm: First Results on the OneMax Problem. (2019) --. (Unpublished)

Chiplunkar, Ankit and Rachelson, Emmanuel and Colombo, Michele and Morlier, Joseph. Approximate inference in related multi-output Gaussian Process Regression. (2017) Lecture Notes in Computer Science. 88-103. ISSN 0302-9743

Regis, Nicolas and Dehais, Frédéric and Rachelson, Emmanuel and Thooris, Charles and Pizziol, Sergio and Causse, Mickaël and Tessier, Catherine. Formal Detection of Attentional Tunneling in Human Operator-Automation Interactions. (2014) IEEE Transactions on Human-Machine Systems, 44 (3). 326-336. ISSN 2168-2291

Conference or Workshop Item

Guillet, Valentin and Wilson, Dennis and Aguilar Melchor, Carlos and Rachelson, Emmanuel. Neural Distillation as a State Representation Bottleneck in Reinforcement Learning. (2022) In: Conference on Lifelong Learning Agents 2022, 18 August 2022 - 24 August 2022 (Montréal, Canada).

Guillet, Valentin and Wilson, Dennis and Aguilar Melchor, Carlos and Rachelson, Emmanuel. On Neural Consolidation for Transfer in Reinforcement Learning. (2022) In: IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning 2022, 4 December 2022 - 7 December 2022 (Singapore, Singapore).

Templier, Paul and Rachelson, Emmanuel and Wilson, Dennis. A geometric encoding for neural network evolution. (2021) In: GECCO '21: Genetic and Evolutionary Computation Conference, 10 July 2021 - 14 July 2021 (Lille, France).

Ikli, S. and Mancel, C. and Mongeau, M. and Olive, Xavier and Rachelson, Emmanuel. An Optimistic Planning Approach for the Aircraft Landing Problem. (2021) In: Electronic Navigation Research Institute - EIWAC 2019, 29 October 2019 - 31 October 2019 (Japan).

Berger, Sandrine and Arroyo-Ramo, Andrea and Guillet, Valentin and Jardin, Thierry and Rachelson, Emmanuel and Bauerheim, Michaël. Towards Reliable and Sample Efficient Deep Reinforcement Learning for Aerodynamics : a Benchmark Application. (2021) In: 74th Annual Meeting of the APS Division of Fluid Dynamics, 21 November 2021 - 23 November 2021 (Phoenix, United States).

Mossina, Luca and Rachelson, Emmanuel and Delahaye, Daniel. Multi-label Classification for the Generation of Sub-problems in Time-constrained Combinatorial Optimization. (2019) In: 8th International Conference on Operations Research and Enterprise Systems (ICORES 2019), 19 February 2019 - 21 February 2019 (Prague, Czech Republic).

Lecarpentier, Erwan and Rachelson, Emmanuel. Non-Stationary Markov Decision Processes a Worst-Case Approach using Model-Based Reinforcement Learning. (2019) In: NeurIPS, 9 December 2019 - 14 December 2019 (Vancouver, Canada).

Mossina, Luca and Rachelson, Emmanuel and Delahaye, Daniel. Application of Multi-label Classification to the Generation of Sub-problems in Combinatorial Optimization. (2018) In: International Workshop on Optimization and Learning: Challenges and Applications (OLA 2018), 26 February 2018 - 28 February 2018 (Alicante, Spain).

Mossina, Luca and Rachelson, Emmanuel. Naive Bayes Classification for Subset Selection in a Multi-label Setting. (2018) In: International Conference on Pattern Recognition and Artificial Intelligence - ICPRAI 2018, 14 May 2018 - 17 May 2018 (Montréal, Canada).

Lecarpentier, Erwan and Infantes, Guillaume and Lesire, Charles and Rachelson, Emmanuel. Open Loop Execution of Tree-Search Algorithms. (2018) In: 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018), 13 July 2018 - 19 July 2018 (Stockholm, Sweden).

Lecarpentier, Erwan and Rapp, Sebastian and Melo, Marc and Rachelson, Emmanuel. Empirical evaluation of a Q-Learning Algorithm for Model-free Autonomous Soaring. (2017) In: Les Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA), 6 July 2017 - 7 July 2017 (Caen, France).

Chiplunkar, Ankit and Rachelson, Emmanuel and Colombo, Michele and Morlier, Joseph. Adding Flight Mechanics to Flight Loads Surrogate Model using Multi-Output Gaussian Processes. (2016) In: 17th AIAA/ISSMO Multidisciplinary Analysis and Optimization Conference, AIAA AVIATION Forum, 13 June 2016 - 17 June 2016 (Washington, United States).

Chiplunkar, Ankit and Rachelson, Emmanuel and Colombo, Michele and Morlier, Joseph. Identification of Physical Parameters Using Change-Point Kernels. (2016) In: SIAM Uncertainty Quantification 2016, 5 April 2016 - 8 April 2016 (Lausanne, Switzerland).

Chiplunkar, Ankit and Rachelson, Emmanuel and Colombo, Michele and Morlier, Joseph. Sparse Physics-based Gaussian Process for Multi-output Regression using Variational Inference. (2016) In: International Conference on Pattern Recognition Applications and Methods, 24 February 2016 - 26 February 2016 (Rome, Italy).

Rachelson, Emmanuel. The Optimal swapping problem during nuclear refueling operations. (2014) In: Acte du 15ème congrès annuel de la Société française de recherche opérationnelle et d’aide à la décision (ROADEF), 26 February 2014 - 28 February 2014 (Bordeaux, France).

Rachelson, Emmanuel and Schnitzler, François and Wehenkel, Louis and Ernst, Damien. Optimal sample selection for batch-mode reinforcement learning. (2011) In: 3rd International Conference on Agents and Artificial Intelligence (ICAART 2011), 28 January 2011 - 30 January 2011 (Rome, Italy).

Rachelson, Emmanuel. Towards a hybrid approach for intra-daily recourse strategies. (2011) In: Conference on Optimization and Practices in Industry (COPI'11), 23 November 2011 - 25 November 2011 (Paris, France).

Rachelson, Emmanuel and Ben Abbes, Ala and Diemer, Sebastien. Combining Mixed Integer Programming and Supervised Learning for Fast Re-planning. (2010) In: 22th International Conference on Tools with Artificial Intelligence - ICTAI 2010, 27 October 2010 - 29 October 2010 (Arras, France).

Ben Abbes, Ala and Rachelson, Emmanuel and Diemer, Sébastien. L’apprentissage au secours de la réduction de dimension pour des problèmes d’optimisation. (2010) In: 12ème Conférence francophone d'Apprentissage Automatique (CAp), 17 May 2010 - 19 May 2010 (Clermont-Ferrand, France).

Rachelson, Emmanuel and Lagoudakis, Michail G.. On the Locality of Action Domination in Sequential Decision Making. (2010) In: 11th International Symposium on Artificial Intelligence and Mathematics (ISIAM 2010), 6 January 2010 - 8 January 2010 (Fort Lauderdale, United States).

Rachelson, Emmanuel and Fabiani, Patrick and Garcia, Frédérick. TiMDPpoly: An Improved Method for Solving Time-Dependent MDPs. (2009) In: International Conference on Tools with Artificial Intelligence - ICTAI 2009, 2009 - 2009 (United States).

Rachelson, Emmanuel and Fabiani, Patrick and Garcia, Frédérick. Adapting an MDP planner to time-dependency: case study on a UAV coordination problem. (2009) In: 4th Workshop on Planning and Plan Execution for Real-World Systems, 19 September 2009 - 23 September 2009 (Thessaloniki, Greece).

Rachelson, Emmanuel and Quesnel, Gauthier and Garcia, Frédérick and Fabiani, Patrick. A Simulation-based Approach for Solving Temporal Markov Problems. (2008) In: European Conference on Artificial Intelligence (ECAI 2008), 21 August 2008 - 25 August 2008 (Patras, Greece).

Rachelson, Emmanuel and Fabiani, Patrick and Garcia, Frédérick. Approximate Policy Iteration for Generalized Semi-Markov Decision Processes: an Improved Algorithm. (2008) In: 8th European Workshop on Reinforcement Learning (EWRL), 30 June 2008 - 3 July 2008 (Villeneuve d'Ascq, France).

Rachelson, Emmanuel and Garcia, Frédérick and Fabiani, Patrick. Extending the Bellman equation for MDPs to continuous actions and continuous time in the discounted case. (2008) In: International Symposium on Artificial Intelligence and Mathematics - 2008, 2008 - 2008 (Fort Lauderdale, United States).

Rachelson, Emmanuel and Fabiani, Patrick and Garcia, Frédérick. Un Algorithme Amélioré d'Itération de la Politique Approchée pour les Processus Décisionnels Semi-Markoviens Généralisés. (2008) In: Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2008), 19 June 2008 - 20 June 2008 (Metz, France).

Rachelson, Emmanuel and Fabiani, Patrick and Garcia, Frédérick and Quesnel, Gauthier. Une Approche basée sur la Simulation pour l'Optimisation des Processus Décisionnels Semi-Markoviens Généralisés. (2008) In: Conférence Francophone d'Apprentissage Automatique (CAp 2008), 29 May 2008 - 31 May 2008 (Ile de Porquerolles, France).

Rachelson, Emmanuel. Temporal coordination under uncertainty: initial results for the two agents case. (2007) In: Doctoral Consortium of the International Conference on Automated Planning and Scheduling - 2007, 22 September 2007 - 26 September 2007 (Rhode Island, United States).

Rachelson, Emmanuel and Teichteil-Königsbuch, Florent and Garcia, Frédérick. XMDP : un modèle de planification temporelle dans l'incertain à actions paramétriques. (2007) In: Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2007), 4 July 2007 - 6 July 2007 (Grenoble, France).

Rachelson, Emmanuel and Fabiani, Patrick and Farges, Jean-Loup and Teichteil-Königsbuch, Florent and Garcia, Frédérick. Une approche du traitement du temps dans le cadre MDP: trois méthodes de découpage de la droite temporelle. (2006) In: Journées Francophones sur la Planification, la Décision et l'Apprentissage pour la conduite de systèmes (JFPDA 2006), 10 May 2006 - 12 May 2006 (Toulouse, France).

Book Section

Garcia, Frédérick and Rachelson, Emmanuel. Markov Decision Processes. (2010) In: Markov Decision Processes in Artificial Intelligence. John Wiley & Sons, Inc., 3-38. ISBN 978-1-84821-167-4

Thesis

Rachelson, Emmanuel. Temporal Markov Decision Problems : Formalization and Resolution. PhD, Systèmes embarqués, Toulouse, France, 2009, 392 p.