publications

2026

1. ICML

   Commit to the Bit: Reactive Reinforcement Learning Done Right

   Onno Eberhard, Claire Vernade, and Michael Muehlebach

   In International Conference on Machine Learning, 2026

   arXiv Bib

   @inproceedings{eberhard2026commit,
     title = {Commit to the Bit: Reactive Reinforcement Learning Done Right},
     author = {Eberhard, Onno and Vernade, Claire and Muehlebach, Michael},
     booktitle = {International Conference on Machine Learning},
     year = {2026},
   }

2. COLT

   Tight Sample Complexity Bounds for Entropic Best Policy Identification

   Amer Essakine, and Claire Vernade

   In Conference on Learning Theory, 2026

   arXiv Bib

   @inproceedings{essakine2026tight,
     title = {Tight Sample Complexity Bounds for Entropic Best Policy Identification},
     author = {Essakine, Amer and Vernade, Claire},
     booktitle = {Conference on Learning Theory},
     year = {2026},
   }

2025

1. EWRL

   Efficient Risk-sensitive Planning via Entropic Risk Measures

   Alexandre Marthe, Samuel Bounan, Aurélien Garivier, and 1 more author

   European Workshop on Reinforcement Learning, 2025

   arXiv Bib

   @article{marthe2025efficient,
     title = {Efficient Risk-sensitive Planning via Entropic Risk Measures},
     author = {Marthe, Alexandre and Bounan, Samuel and Garivier, Aur{\'e}lien and Vernade, Claire},
     journal = {European Workshop on Reinforcement Learning},
     year = {2025},
   }

2. NeurIPS

   Non-Stationary Lipschitz Bandits

   Nicolas Nguyen, Solenne Gaucher, and Claire Vernade

   In Advances in Neural Information Processing Systems, 2025

   arXiv Bib

   @inproceedings{nguyen2025nonstationary,
     title = {Non-Stationary Lipschitz Bandits},
     author = {Nguyen, Nicolas and Gaucher, Solenne and Vernade, Claire},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2025},
   }

3. ICML

   Partially Observable Reinforcement Learning with Memory Traces

   Onno Eberhard, Michael Muehlebach, and Claire Vernade

   In International Conference on Machine Learning, 2025

   arXiv Bib

   @inproceedings{eberhard2025partially,
     title = {Partially Observable Reinforcement Learning with Memory Traces},
     author = {Eberhard, Onno and Muehlebach, Michael and Vernade, Claire},
     booktitle = {International Conference on Machine Learning},
     year = {2025},
   }

4. AISTATS

   Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits

   Nicolas Nguyen, Imad Aouali, András György, and 1 more author

   In International Conference on Artificial Intelligence and Statistics, 2025

   arXiv Bib

   @inproceedings{nguyen2025prior,
     title = {Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits},
     author = {Nguyen, Nicolas and Aouali, Imad and Gy{\"o}rgy, Andr{\'a}s and Vernade, Claire},
     booktitle = {International Conference on Artificial Intelligence and Statistics},
     year = {2025},
   }

2024

1. Preprint

   A Pontryagin Perspective on Reinforcement Learning

   Onno Eberhard, Claire Vernade, and Michael Muehlebach

   arXiv preprint, 2024

   arXiv Bib

   @article{eberhard2024pontryagin,
     title = {A Pontryagin Perspective on Reinforcement Learning},
     author = {Eberhard, Onno and Vernade, Claire and Muehlebach, Michael},
     journal = {arXiv preprint},
     year = {2024},
   }

2. RLC

   Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms

   MohammadJavad Azizi, Thang Duong, Yasin Abbasi-Yadkori, and 3 more authors

   In Reinforcement Learning Conference, 2024

   arXiv Bib

   @inproceedings{azizi2024nonstationary,
     title = {Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms},
     author = {Azizi, MohammadJavad and Duong, Thang and Abbasi-Yadkori, Yasin and Gy{\"o}rgy, Andr{\'a}s and Vernade, Claire and Ghavamzadeh, Mohammad},
     booktitle = {Reinforcement Learning Conference},
     year = {2024},
   }

2023

1. NeurIPS

   Beyond Average Return in Markov Decision Processes

   Alexandre Marthe, Aurélien Garivier, and Claire Vernade

   In Advances in Neural Information Processing Systems, 2023

   arXiv Bib

   @inproceedings{marthe2023beyond,
     title = {Beyond Average Return in Markov Decision Processes},
     author = {Marthe, Alexandre and Garivier, Aur{\'e}lien and Vernade, Claire},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2023},
   }

2026

1. Preprint

   To Retain or to Adapt? Generalizing Continual Learning

   Giulia Lanzillotta, Mandana Samiei, Doina Precup, and 2 more authors

   arXiv preprint, 2026

   arXiv Bib

   @article{lanzillotta2026retain,
     title = {To Retain or to Adapt? Generalizing Continual Learning},
     author = {Lanzillotta, Giulia and Samiei, Mandana and Precup, Doina and Pascanu, Razvan and Vernade, Claire},
     journal = {arXiv preprint},
     year = {2026},
   }

2. Preprint

   Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation

   Ziyad Sheebaelhamd, Luca Viano, Volkan Cevher, and 1 more author

   arXiv preprint, 2026

   arXiv Bib

   @article{sheebaelhamd2026split,
     title = {Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation},
     author = {Sheebaelhamd, Ziyad and Viano, Luca and Cevher, Volkan and Vernade, Claire},
     journal = {arXiv preprint},
     year = {2026},
   }

2025

1. NeurIPS

   Quantization-Free Autoregressive Action Transformer

   Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach, and 1 more author

   In Advances in Neural Information Processing Systems, 2025

   arXiv Bib

   @inproceedings{sheebaelhamd2025quantization,
     title = {Quantization-Free Autoregressive Action Transformer},
     author = {Sheebaelhamd, Ziyad and Tschannen, Michael and Muehlebach, Michael and Vernade, Claire},
     booktitle = {Advances in Neural Information Processing Systems},
     year = {2025},
   }