62 citations · 175 across the 40 of their papers we have counts for
25 papers · 1 filter
On the instability of local learning algorithms: Q-learning can fail in infinite state spaces
Urtzi Ayesta, Sergey Foss, Matthieu Jonckheere +1
We investigate the challenges of applying model-free reinforcement learning algorithms, like online Q-learning, to infinite state space Markov Decision Processes (MDPs). We first i…
Decision-Epoch Matters: Unveiling its Impact on the Stability of Scheduling with Randomly Varying Connectivity
Nahuel Soprano-Loto, Urtzi Ayesta, Matthieu Jonckheere +1
A classical queuing theory result states that in a parallel-queue single-server model, the maximum stability region does not depend on the scheduling decision epochs, and in partic…
Online matching for the multiclass stochastic block model
Nahuel Soprano-Loto, Matthieu Jonckheere, Pascal Moyal
We consider the problem of sequential matching in a stochastic block model with several classes of nodes and generic compatibility constraints. When the probabilities of connection…
Persistence in a large network of locally interacting neurons
Maximiliano Altamirano, Roberto Cortez, Matthieu Jonckheere +1
This article presents a biological neural network model driven by inhomogeneous Poisson processes accounting for the intrinsic randomness of synapses. The main novelty is the intro…
Generalized max-weight policies in stochastic matching
Matthieu Jonckheere, Pascal Moyal, Claudia Ramírez +1
We consider a matching system where items arrive one by one at each node of a compatibility network according to Poisson processes and depart from it as soon as they are matched to…
Sequential Algorithms and Independent Sets Discovering on Large Sparse Random Graphs
Paola Bermolen, Matthieu Jonckheere, Federico Larroca +1
Computing the size of maximum independent sets is a NP-hard problem for fixed graphs. Characterizing and designing efficient algorithms to estimate this independence number for ran…