Scholar
Victor Boone
Google Scholar ID: UAIjjuEAAAAJ
Post Doc, Université Grenoble Alpes
Citations & Impact
Citations
64
H-index
5
i10-index
2
Publications
14
Co-authors
0
Publications
Resume (English only)
Academic Achievements
- Published 'Asymptotically optimal regret in communicating Markov decision processes' in 2025; Completed PhD thesis 'Optimal regrets in Markov decision processes' in 2024 and received the prix de thèse UGA 2025; Published 'Achieving Tractable Minimax Optimal Regret in Average Reward MDPs' at NeurIPS 2024; Published 'The Sliding Regret in Stochastic Bandits: Discriminating Index and Randomized Policies' in 2023.
Research Experience
- Currently a Post-Doc at the Institut de Recherche en Informatique de Toulouse (IRIT). Has also been a Post-Doc at Grenoble and visited Urtzi Ayesta's team in Toulouse.
Education
- PhD thesis supervised by Bruno Gaujal and Panayotis Mertikopoulos, defended in November 2024. The thesis is entirely dedicated to regret minimization in Markov decision processes in the undiscounted infinite horizon setting.
Background
- Research interests include Reinforcement Learning, Multi-Armed Bandits, Game Theory, and Queuing Theory. Aims to explain the results of learning algorithms run on his computer by pushing theory to its limits, focusing on finite Markov decision processes, stochastic bandits, and finite games in normal form.
Miscellany
- Email: victor.boone@irit.fr, boonevv@gmail.com.
Co-authors