papers

Dynamic Learning Rate for Deep Reinforcement Learning: A Bandit Approach
In Deep Reinforcement Learning models trained using gradient-based techniques, the choice of optimizer and its learning rate are …
Henrique DONANCIO, Antoine BARRIER, Leah SOUTH, Florence FORBES
17 octobre 2024
PDF arXiv BibTeX
MARVEL: MR Fingerprinting with Additional micRoVascular Estimates using bidirectional LSTMs
The Magnetic Resonance Fingerprinting (MRF) approach aims to estimate multiple MR or physiological parameters simultaneously with a …
Antoine BARRIER, Thomas COUDERT, Aurélien DELPHIN, Benjamin LEMASSON, Thomas CHRISTEN
1 mai 2024
PDF Poster HAL arXiv Code BibTeX
Contributions à une théorie de l'exploration pure en statistique séquentielle
Cette thèse, à la croisée entre les domaines de l’intelligence artificielle, de la statistique séquentielle et de l’optimisation, …
Antoine BARRIER
20 juillet 2023
PDF Slides Thèse HAL BibTeX
On Best-Arm Identification with a Fixed Budget in Non-Parametric Multi-Armed Bandits
We lay the foundations of a non-parametric theory of best-arm identification in multi-armed bandits with a fixed budget T. We consider …
Antoine BARRIER, Aurélien GARIVIER, Gilles STOLTZ
1 mars 2023
PDF Slides PMLR HAL arXiv BibTeX
A Non-Asymptotic Approach to Best-Arm Identification for Gaussian Bandits
We propose a new strategy for best-arm identification with fixed confidence and show non-asymptotic bounds for Gaussian variables with bounded means and unit variance.
Antoine BARRIER, Aurélien GARIVIER, Tomáš KOCÁK
1 avril 2022
PDF Poster Video & slides PMLR HAL arXiv BibTeX
A Non-Asymptotic Approach to Best-Arm Identification for Gaussian Bandits