Contact: louis-sebastien.rebuffi at inria.frCurrent Position:
I am a PhD student at Université Grenoble Alpes, in the Laboratoire d’Informatique de Grenoble (LIG), supervised by Bruno Gaujal and Jonatha Anselmi, studying reinforcement learning algorithms applied to controlled queuing systems, viewing them as Markov decision processes (MDP). I am mainly interested in performance evaluation, control and optimization of distributed system and reinforcement learning.
Publications:
- J. Anselmi, B. Gaujal and L.S. Rebuffi, Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space, Neurips 2022 Preprint (accepted).
- J. Anselmi, B. Gaujal and L.S. Rebuffi, Optimal Speed Profile of a DVFS Processor under Soft Deadlines, Performance Evaluation, Vol. 152, 2021, 102245. Video for the conference at Performance 2021
Talks and Other:
- Workshop YEQT XV “Machine Learning for Stochastic Networks” in November 2022, at Eindhoven University of Technology.
- ROADEF2022: 23e congrès annuel de la Société Française de Recherche Opérationnelle et d’Aide à la Décision in February 2022, Lyon. Paper presented: Optimal Speed of a DVFS Processor under Soft Deadlines
- Workshop “Modern Trends in Controlled Stochastic Processes: Theory and Applications” in July 2021, at University of Liverpool (remote).
