In this thesis, we study strategies for sequential resource allocation, under the so-called stochastic multi-armed bandit model. In this model, when an agent draws an arm, he receives as a reward a realization from a probability distribution associated to the arm. In this document, we consider two different bandit problems. In the reward maximization objective, the agent aims at maximizing the sum of rewards obtained during his interaction with the bandit, whereas in the best arm identification objective, his goal is to find the set of m best arms (i.e. arms with highest mean reward), without suffering a loss when drawing ‘bad’ arms. For these two objectives, we propose strategies, also called bandit algorithms, that are optimal (or close t...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
Cette thèse s'inscrit dans les domaines de l'apprentissage statistique et de la statistique séquenti...
In this thesis, we study strategies for sequential resource allocation, under the so-called stochast...
Dans cette thèse, nous étudions des stratégies d’allocation séquentielle de ressources. Le modèle st...
This document presents in a unified way different results about the optimal solution of several mult...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
This document presents in a unified way different results about the optimal solution of several mult...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
This thesis lies in the fields of artificial intelligence, sequential statistics and optimization. W...
This thesis lies in the fields of artificial intelligence, sequential statistics and optimization. W...
This thesis lies in the fields of artificial intelligence, sequential statistics and optimization. W...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
Cette thèse s'inscrit dans les domaines de l'apprentissage statistique et de la statistique séquenti...
In this thesis, we study strategies for sequential resource allocation, under the so-called stochast...
Dans cette thèse, nous étudions des stratégies d’allocation séquentielle de ressources. Le modèle st...
This document presents in a unified way different results about the optimal solution of several mult...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
This document presents in a unified way different results about the optimal solution of several mult...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
This thesis lies in the fields of artificial intelligence, sequential statistics and optimization. W...
This thesis lies in the fields of artificial intelligence, sequential statistics and optimization. W...
This thesis lies in the fields of artificial intelligence, sequential statistics and optimization. W...
International audienceWe consider the problem of finding the best arm in a stochastic multi-armed ba...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
International audienceWe study a generalization of the multi-armed bandit problem with multiple p...
Cette thèse s'inscrit dans les domaines de l'apprentissage statistique et de la statistique séquenti...