Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Allesiardo, Robin"'
Autor:
Allesiardo, Robin
Le problème des bandits manchots est un cadre théorique permettant d'étudier le compromis entre exploration et exploitation lorsque l'information observée est partielle. Dans celui-ci, un joueur dispose d'un ensemble de K bras (ou actions), chacu
Externí odkaz:
http://www.theses.fr/2016SACLS334/document
We consider a non-stationary formulation of the stochastic multi-armed bandit where the rewards are no longer assumed to be identically distributed. For the best-arm identification task, we introduce a version of Successive Elimination based on rando
Externí odkaz:
http://arxiv.org/abs/1609.02139
To address the contextual bandit problem, we propose an online random forest algorithm. The analysis of the proposed algorithm is based on the sample complexity needed to find the optimal decision stump. Then, the decision stumps are assembled in a r
Externí odkaz:
http://arxiv.org/abs/1504.06952
This paper presents a new contextual bandit algorithm, NeuralBandit, which does not need hypothesis on stationarity of contexts and rewards. Several neural networks are trained to modelize the value of rewards knowing the context. Two variants, based
Externí odkaz:
http://arxiv.org/abs/1409.8191
Publikováno v:
WI-IAT 2021-20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology
WI-IAT 2021-20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Dec 2021, Melbourne, Australia. pp.1-8, ⟨10.1145/3486622.3493941⟩
WI-IAT 2021-20th IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, Dec 2021, Melbourne, Australia. pp.1-8, ⟨10.1145/3486622.3493941⟩
International audience; Exposing latent structure (graph, tree...) of data is a major challenge to deal with the web of data. Today's embedding techniques incorporate any data source (noisy graphs, item similarities, plain text) into continuous vecto
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::be298b7d4b938271bb91b2edcea00913
https://hal.science/hal-03494697/document
https://hal.science/hal-03494697/document
Publikováno v:
Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)
LREC 2020-12th Conference on Language Resources and Evaluation
LREC 2020-12th Conference on Language Resources and Evaluation, May 2020, Marseille, France. pp.4789-4797
LREC 2020-12th Conference on Language Resources and Evaluation
LREC 2020-12th Conference on Language Resources and Evaluation, May 2020, Marseille, France. pp.4789-4797
International audience; Word embeddings intervene in a wide range of natural language processing tasks. These geometrical representations are easy to manipulate for automatic systems. Therefore, they quickly invaded all areas of language processing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::33331676359ae146a0f73fde5efb842f
https://inria.hal.science/hal-02919006
https://inria.hal.science/hal-02919006
Publikováno v:
International Journal of Data Science & Analytics; Mar2021, Vol. 11 Issue 2, p85-103, 19p
Autor:
Allesiardo, Robin
Publikováno v:
Intelligence artificielle [cs.AI]. Université Paris Saclay (COmUE), 2016. Français. ⟨NNT : 2016SACLS334⟩
The multi-armed bandit is a framework allowing the study of the trade-off between exploration and exploitation under partial feedback. At each turn t Є [1,T] of the game, a player has to choose an arm kt in a set of K and receives a reward ykt drawn
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::888e63431b935a18e83a880da79de20f
https://hal.inria.fr/tel-01420663v3
https://hal.inria.fr/tel-01420663v3
Publikováno v:
CAP'14
CAP'14, Jul 2014, St-Etienne, France. pp.11-19
CAP'14, Jul 2014, St-Etienne, France. pp.11-19
National audience; Dans cet article, nous proposons un nouvel algorithme de bandits contextuels, NeuralBandit, ne faisant aucune hypothèse de stationnarité sur les contextes et les récompenses. L'algorithme proposé utilise plusieurs perceptrons m
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::aa3401fda4688b8d495f994e7af80017
https://hal.science/hal-01055521
https://hal.science/hal-01055521
Autor:
Allesiardo, Robin, Feraud, Raphael
Publikováno v:
2015 IEEE International Conference on Data Science & Advanced Analytics (DSAA); 2015, p1-7, 7p