Understanding the dynamics of complex systems, and how to optimally act in them impacts all aspects of human societies where a careful management of natural, energetic, human and computational resources is required. To overcome the limitations of human capabilities to process large amounts of data, researchers from the field of machine learning and mathematical statistics for sequential decision making pursue the long-term goal of developing an optimal and automatic method that can, from partial observations and sequential interactions with a complex system, learn an optimal behavior. While optimal control considers the dynamics of the system is assumed to be known, reinforcement learning is interested in the case when the dynamics is unkno...
We study structured multi-armed bandits, which is the problem of online decision-making under uncert...
This thesis is dedicated to the study of resource allocation problems in uncertain environments, whe...
Dans cette thèse nous étudions différentes généralisations du problème dit « du bandit manchot ». Le...
We consider a multi-armed bandit problem specified by a set of Gaussian or Bernoulli distributions e...
We study a structured variant of the multi-armed bandit problem specified by a set of Bernoulli dist...
Cette thèse traite des domaines suivant en Apprentissage Automatique: la théorie des Bandits, l'Appr...
Cette thèse traite des domaines suivant en Apprentissage Automatique: la théorie des Bandits, l'Appr...
This thesis studies several extensions of multi-armed bandit problem, where a learner sequentially s...
Sequential decision making is a core component of many real-world applications, from computer-networ...
The multi-armed bandit is a framework allowing the study of the trade-off between exploration and ex...
This thesis studies the following topics in Machine Learning: Bandit theory, Statistical learning an...
The main topics adressed in this thesis lie in the general domain of sequential learning, and in par...
We investigate the structural properties of certain sequential decision-making problems with limited...
The multi-armed bandit(MAB) problem is a simple yet powerful framework that has been extensively stu...
International audienceWe consider a multi-armed bandit problem specified by a set of one-dimensional...
We study structured multi-armed bandits, which is the problem of online decision-making under uncert...
This thesis is dedicated to the study of resource allocation problems in uncertain environments, whe...
Dans cette thèse nous étudions différentes généralisations du problème dit « du bandit manchot ». Le...
We consider a multi-armed bandit problem specified by a set of Gaussian or Bernoulli distributions e...
We study a structured variant of the multi-armed bandit problem specified by a set of Bernoulli dist...
Cette thèse traite des domaines suivant en Apprentissage Automatique: la théorie des Bandits, l'Appr...
Cette thèse traite des domaines suivant en Apprentissage Automatique: la théorie des Bandits, l'Appr...
This thesis studies several extensions of multi-armed bandit problem, where a learner sequentially s...
Sequential decision making is a core component of many real-world applications, from computer-networ...
The multi-armed bandit is a framework allowing the study of the trade-off between exploration and ex...
This thesis studies the following topics in Machine Learning: Bandit theory, Statistical learning an...
The main topics adressed in this thesis lie in the general domain of sequential learning, and in par...
We investigate the structural properties of certain sequential decision-making problems with limited...
The multi-armed bandit(MAB) problem is a simple yet powerful framework that has been extensively stu...
International audienceWe consider a multi-armed bandit problem specified by a set of one-dimensional...
We study structured multi-armed bandits, which is the problem of online decision-making under uncert...
This thesis is dedicated to the study of resource allocation problems in uncertain environments, whe...
Dans cette thèse nous étudions différentes généralisations du problème dit « du bandit manchot ». Le...