Bianca Marin Moreno

PhD student at INRIA and EDF R&D. Contact me at bianca.marin-moreno_at_inria.fr.

prof_pic.jpg

I am a second year PhD student at INRIA Thoth, and at EDF R&D. I work under the supervision of Pierre Gaillard, from INRIA, Nadia Oudjane, from EDF R&D and Margaux Brégère, from both EDF R&D and Sorbonne Université probability, statistics and modelisation lab (LPSM).

My research focuses on the intersection of reinforcement learning and online learning algorithms, particularly within the context of mean field games and mean field control. I am interested in understanding the theoretical aspects of sequential decision making while also exploring their practical applications in energy management scenarios.

News

Oct 01, 2024 Our paper MetaCURL: Non-stationary Concave Utility Reinforcement Learning has been accepted to NeurIPS 2024! This is also a joint work with Pierre Gaillard, Margaux Brégère and Nadia Oudjane. Come and check it out at NeurIPS@Paris or at Vancouver!
Aug 07, 2024 I will be visiting Nicolò Cesa-Bianchi at the Laboratory for Artificial Intelligence and Learning Algorithms from the University of Milan and Marcello Restelli at Politecnico di Milano in the fall of 2024.
Aug 01, 2024 Happy to announce that our paper MetaCURL: Non-stationary Concave Utility Reinforcement Learning has been accepted to the EWRL 2024. See you in Toulouse!
Jan 20, 2024 Happy to announce that the paper Efficient Model-Based Concave Utility Reinforcement Learning through Greedy Mirror Descent has been accepted to AISTATS 2024. This is a joint work with Pierre Gaillard, Margaux Brégère and Nadia Oudjane.