- Laboratoire d'Informatique de GrenobleFR2 papers
- Université Grenoble AlpesFR2 papers
- Centre Inria de l'Université Grenoble AlpesFR1 paper
- Centre National de la Recherche ScientifiqueFR1 paper
- Institut des langues et cultures d'Europe, Amérique, Afrique, Asie et AustralieFR1 paper
- Institut national de recherche en sciences et technologies du numériqueFR1 paper
3 papers
cs.LG2023
Reinforcement Learning in a Birth and Death Process: Breaking the Dependence on the State Space
Jonatha Anselmi, Bruno Gaujal, Louis-Sébastien Rebuffi
In this paper, we revisit the regret of undiscounted reinforcement learning in MDPs with a birth and death structure. Specifically, we consider a controlled queue with impatient jo…
cs.PF2020
Exponential Convergence Rate for the Asymptotic Optimality of Whittle Index Policy
Nicolas Gast, Bruno Gaujal, Chen Yan
We evaluate the performance of Whittle index policy for restless Markovian bandits, when the number of bandits grows. It is proven in [30] that this performance is asymptotically o…
cs.DC2019
DGEMM performance is data-dependent
Tom Cornebize, Arnaud Legrand
The DGEMM function is a widely used implementation of the matrix product. While the asymptotic complexity of the algorithm only depends on the sizes of the matrices, we show that t…