Matches in SemOpenAlex for { <https://semopenalex.org/work/W2595842594> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W2595842594 abstract "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 to optimal), in a sense precised below. Maximizing the sum of rewards is equivalent to minimizing a quantity called regret. Thanks to an asymptotic lower bound on the regret of any uniformly efficient algorithm given by Lai and Robbins, one can define asymptotically optimal algorithms as algorithms whose regret reaches this lower bound. In this thesis, we propose, for two Bayesian algorithms, Bayes-UCB and Thompson Sampling, a finite-time analysis, that is a non-asymptotic upper bound on their regret, in the particular case of bandits with binary rewards. This upper bound allows to establish the asymptotic optimality of both algorithms. In the best arm identification framework, a possible goal is to determine the number of samples of the armsneeded to identify, with high probability, the set of m best arms. We define a notion of complexity for best arm identification in two different settings considered in the literature: the fixed-budget and fixed-confidence settings. We provide new lower bounds on these complexity terms and we analyse new algorithms, some of which reach the lower bound in particular cases of two-armed bandit models and are therefore optimal" @default.
- W2595842594 created "2017-03-23" @default.
- W2595842594 creator A5083219425 @default.
- W2595842594 date "2014-10-01" @default.
- W2595842594 modified "2023-09-24" @default.
- W2595842594 title "Analysis of bayesian and frequentist strategies for sequential resource allocation" @default.
- W2595842594 hasPublicationYear "2014" @default.
- W2595842594 type Work @default.
- W2595842594 sameAs 2595842594 @default.
- W2595842594 citedByCount "1" @default.
- W2595842594 countsByYear W25958425942021 @default.
- W2595842594 crossrefType "dissertation" @default.
- W2595842594 hasAuthorship W2595842594A5083219425 @default.
- W2595842594 hasConcept C105795698 @default.
- W2595842594 hasConcept C107673813 @default.
- W2595842594 hasConcept C123197309 @default.
- W2595842594 hasConcept C126255220 @default.
- W2595842594 hasConcept C134306372 @default.
- W2595842594 hasConcept C160234255 @default.
- W2595842594 hasConcept C162376815 @default.
- W2595842594 hasConcept C177264268 @default.
- W2595842594 hasConcept C181789720 @default.
- W2595842594 hasConcept C199360897 @default.
- W2595842594 hasConcept C2776330181 @default.
- W2595842594 hasConcept C33923547 @default.
- W2595842594 hasConcept C41008148 @default.
- W2595842594 hasConcept C50817715 @default.
- W2595842594 hasConcept C73602740 @default.
- W2595842594 hasConcept C77553402 @default.
- W2595842594 hasConceptScore W2595842594C105795698 @default.
- W2595842594 hasConceptScore W2595842594C107673813 @default.
- W2595842594 hasConceptScore W2595842594C123197309 @default.
- W2595842594 hasConceptScore W2595842594C126255220 @default.
- W2595842594 hasConceptScore W2595842594C134306372 @default.
- W2595842594 hasConceptScore W2595842594C160234255 @default.
- W2595842594 hasConceptScore W2595842594C162376815 @default.
- W2595842594 hasConceptScore W2595842594C177264268 @default.
- W2595842594 hasConceptScore W2595842594C181789720 @default.
- W2595842594 hasConceptScore W2595842594C199360897 @default.
- W2595842594 hasConceptScore W2595842594C2776330181 @default.
- W2595842594 hasConceptScore W2595842594C33923547 @default.
- W2595842594 hasConceptScore W2595842594C41008148 @default.
- W2595842594 hasConceptScore W2595842594C50817715 @default.
- W2595842594 hasConceptScore W2595842594C73602740 @default.
- W2595842594 hasConceptScore W2595842594C77553402 @default.
- W2595842594 hasLocation W25958425941 @default.
- W2595842594 hasOpenAccess W2595842594 @default.
- W2595842594 hasPrimaryLocation W25958425941 @default.
- W2595842594 hasRelatedWork W1488797257 @default.
- W2595842594 hasRelatedWork W1673501158 @default.
- W2595842594 hasRelatedWork W1911551976 @default.
- W2595842594 hasRelatedWork W2187410796 @default.
- W2595842594 hasRelatedWork W2281970206 @default.
- W2595842594 hasRelatedWork W2296579470 @default.
- W2595842594 hasRelatedWork W2301683925 @default.
- W2595842594 hasRelatedWork W2398037065 @default.
- W2595842594 hasRelatedWork W2763449826 @default.
- W2595842594 hasRelatedWork W2793854160 @default.
- W2595842594 hasRelatedWork W2886983457 @default.
- W2595842594 hasRelatedWork W2890134435 @default.
- W2595842594 hasRelatedWork W2945291882 @default.
- W2595842594 hasRelatedWork W2946909365 @default.
- W2595842594 hasRelatedWork W2951155041 @default.
- W2595842594 hasRelatedWork W2955643364 @default.
- W2595842594 hasRelatedWork W3029674688 @default.
- W2595842594 hasRelatedWork W3034273763 @default.
- W2595842594 hasRelatedWork W3104156937 @default.
- W2595842594 hasRelatedWork W3115017114 @default.
- W2595842594 isParatext "false" @default.
- W2595842594 isRetracted "false" @default.
- W2595842594 magId "2595842594" @default.
- W2595842594 workType "dissertation" @default.