Apprentissage par renforcement

@inproceedings{forghieri25,
  author = {Forghieri, O. and Carlinet, Y. and Hyon, E. and Le Pennec, E. and Perrot, N.},
  title = {Faster Latency Constrained Service Placement in Edge Computing with Deep Reinforcement Learning Methods},
  booktitle = {TX4NETs Workshop, IFIP NETWORKING Conference},
  year = {2025}
}

@inproceedings{clavier24c,
  author = {Clavier, P. and Shi, L. and Le Pennec, E. and Mazumdar, E. and Wierman, A. and Geist, M.},
  title = {Near-Optimal Distributionally Robust RL with General $L_p$ Norms},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  volume = {37},
  pages = {1750--1810},
  year = {2024},
  doi = {10.52202/079017-0056}
}

@inproceedings{clavier24b,
  author = {Clavier, P. and Rachelson, E. and Le Pennec, E. and Geist, M.},
  title = {Bootstrapping Expectiles in Reinforcement Learning},
  booktitle = {17th European Workshop on Reinforcement Learning},
  year = {2024},
  eprint = {2406.04081},
  archiveprefix = {arXiv}
}

@inproceedings{Forghieri24b,
  author = {Forghieri, O. and Castel, H. and Hyon, E. and Le Pennec, E.},
  title = {State Abstraction Discovery from Progressive Disaggregation Methods},
  booktitle = {17th European Workshop on Reinforcement Learning},
  year = {2024}
}

@inproceedings{clavier24,
  author = {Clavier, P. and Le Pennec, E. and Geist, M.},
  title = {Towards Minimax Optimality of Model-based Robust Reinforcement Learning},
  booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)},
  series = {PMLR},
  volume = {244},
  pages = {820--855},
  year = {2024},
  eprint = {2302.05372},
  archiveprefix = {arXiv}
}

@inproceedings{Forghieri24,
  author = {Forghieri, O. and Castel, H. and Hyon, E. and Le Pennec, E.},
  title = {Progressive State Space Disaggregation for Infinite Horizon Dynamic Programming},
  booktitle = {International Conference on Automated Planning and Scheduling},
  volume = {34},
  pages = {221--229},
  year = {2024},
  doi = {10.1609/icaps.v34i1.31479}
}

@inproceedings{Forghieri24c,
  author = {Forghieri, O. and Castel, H. and Le Pennec, E. and Hyon, E.},
  title = {Progressive state space disaggregation for dynamic programming},
  booktitle = {25e Congrès Annuel de la Société Française de Recherche Opérationnelle et d'Aide à la Décision (ROADEF)},
  address = {Amiens},
  year = {2024}
}

@patent{allassonniere21,
  author = {Allassonnière, S. and Besson, R. and Le Pennec, E.},
  title = {Real-time diagnosis aid method and decision-support for medical diagnosis to a user of a medical system},
  number = {US11881309B2},
  year = {2024}
}

@article{clavier22,
  author = {Clavier, P. and Allassonnière, S. and Le Pennec, E.},
  title = {Robust Reinforcement Learning with Distributional Risk-averse formulation},
  journal = {arXiv},
  year = {2022},
  eprint = {2206.06841},
  archiveprefix = {arXiv}
}

@inproceedings{Besson21,
  author = {Besson, R. and Le Pennec, E. and Allassonnière, S.},
  title = {A Model-Based Reinforcement Learning Approach for a Rare Disease Diagnostic Task},
  booktitle = {Proceedings of Entropy 2021: The Scientific Tool of the 21st Century},
  year = {2021},
  doi = {10.3390/entropy2021-09749}
}

@article{Loge21,
  author = {Logé, F. and Le Pennec, E. and Amadou-Boubacar, H.},
  title = {Intelligent Questionnaires Using Approximate Dynamic Programming},
  journal = {i-com},
  number = {3},
  volume = {19},
  pages = {227-237},
  year = {2020},
  doi = {10.1515/icom-2020-0022}
}

@inproceedings{LogeDSHealh20,
  author = {Logé, F. and Le Pennec, E. and Amadou-Boubacar, H.},
  title = {Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning},
  booktitle = {2020 KDD Workshop on Applied Data Science for Healthcare},
  year = {2020},
  eprint = {2007.11880},
  archiveprefix = {arXiv}
}

@inproceedings{LogeUCAI20,
  author = {Logé, F. and Le Pennec, E. and Amadou-Boubacar, H.},
  title = {Adaptive predictive-questionnaire by approximate dynamic programming},
  booktitle = {Workshop on User-Centered Artificial Intelligence (UCAI), Mensch und Computer 2020},
  year = {2020},
  doi = {10.18420/muc2020-ws111-264}
}

@inproceedings{BessonIcaart20,
  author = {Besson, R. and Le Pennec, E. and Spaggiari, E. and Neuraz, A. and Stirnemann, J. and Allassonnière, S.},
  title = {Optimization of a Sequential Decision Making Problem for a Rare Disease Diagnostic Application},
  booktitle = {ICAART 2020},
  pages = {475--482},
  year = {2020},
  doi = {10.5220/0008938804750482}
}

@article{Besson19,
  author = {Besson, R. and Le Pennec, E. and Allassonnière, S.},
  title = {Learning from both experts and data},
  journal = {Entropy},
  number = {12},
  volume = {21},
  pages = {1208},
  year = {2019},
  doi = {10.3390/e21121208},
  eprint = {1910.09043},
  archiveprefix = {arXiv}
}

@inproceedings{Levent19,
  author = {Levent, T. and Preux, Ph. and Le Pennec, E. and Badosa, J. and Henri, G. and Bonnassieux, Y.},
  title = {Energy Management for Microgrids: a Reinforcement Learning Approach},
  booktitle = {IEEE ISGT Europe},
  pages = {1--5},
  year = {2019},
  doi = {10.1109/ISGTEurope.2019.8905538}
}

@article{Besson18,
  author = {Besson, R. and Le Pennec, E. and Allassonnière, S. and Stirnemann, J. and Spaggiari, E. and Neuraz, A.},
  title = {A Model-Based Reinforcement Learning Approach for a Rare Disease Diagnostic Task},
  journaltitle = {Preprint},
  year = {2018},
  eprint = {1811.10112},
  archiveprefix = {arXiv}
}

@inproceedings{BessonSfdS17,
  author = {Besson, R. and Le Pennec, E. and Allassonnière, S.},
  title = {Optimisation d'arbre de décision pour un problème de détection précoce d'anomalies foetales},
  booktitle = {Journée de la SFdS},
  address = {Avignon},
  year = {2017}
}