Dating

SequeL team

Sequential Learning

Leader: Philippe Preux

PRESENTATION MEMBERS THESES PUBLICATIONS

Presentation

SequeL is a research group working in the field of machine learning; more specifically, SequeL is dedicated to the study of the problem of sequential decision making under uncertainty, that is, the study of how an "agent" having a goal to fullfill can learn an optimal behavior to achieve this goal in an unknown environment. SequeL is composed of two dozens members. Activities range from foundations of learning to algorithm design, and transfer towards companies. Questions are studied such as "What can a Turing machine learn efficiently? and in which conditions?". Or, in a budget context, "Given an amount of computational resource, how close to the optimal behavior can an algorithm reach?", finally application oriented questions such as those related to computational advertizing and recommendation systems for e-commerce websites, are also studied.

SequeL has led to the multi-awarded Crazy Stone go playing program.  Some SequeL PhD students have been awarded  the Gilles Kahn award, the Jacques Neveu award and the ECCAI award. We won the ICML 2011 Exploration vs. Exploitation challenge, and the ACM RecSYS 2014 challenge (both challenges on recommendation systems). SequeL expertize has led to collaborations with international companies like Orange Labs, Intel, Technicolor, Deezer and also with national and local SMEs.

 

Members

Permanent

  • Professor
    • Philippe Preux (Responsable)
  • Research director
    • Rémi Munos
  • Research scientists
    • Emilie Kaufmann
    • Alessandro Lazaric
    • Odalric-Ambrym Maillard
    • Daniil Ryabko
    • Michal Valko

Temporary

  • Postdoc
    • Mohammad sadegh Talebi
  • Phd students
    • Sheikh Waqas Akhtar
    • Merwan Barlier
    • Nicolas Carrara
    • Omar Darwiche Domingues
    • Yannis Flet-berliac
    • Ronan Fruit
    • Guillaume Gautier
    • Edouard Leurent
    • Pierre Perrault
    • Hassan Saber
    • Mathieu Seurin
    • Julien Seznec
    • Xuedong Shang
    • Florian Strub
    • Kiewan Villatel
  • Other
    • Lilian Besson

Associated

  • Professor
    • Olivier Pietquin

Merwan Barlier

Dialogues intelligents basés sur l'écoute de conversation homme/homme

Nicolas Carrara

Apprentissage par renforcement pour optimisation de systèmes de dialogue via l'adaptation à chaque utilisateur

Omar Darwiche Domingues

Sequential Learning in Dynamic Environments

Yannis Flet-berliac

Deep Reinforcement Learning in Stochastic and non Stationary Environments

Ronan Fruit

Transfer of Knowledge in reinforcement learning for the improvement of exploration and generalization

Guillaume Gautier

Fast sampling of determinantal point processes

Jean-Bastien Grill

Création et analyse d'algorithmes efficaces pour la prise de décision dans un environnement inconnu et incertain

Edouard Leurent

Conduite automobile autonome : application des techniques d'apprentissage automatique à la planification contextualisée de trajectoire

Pierre Perrault

Online Learning on Streaming Graphs

Hassan Saber

Structure adaptation in reinforcement learning

Mathieu Seurin

Problème de récompenses Multi'échelle dans le contexte de l'apprentissage par renforcement

Julien Seznec

Sequential Learning for Educationnal System

Xuedong Shang

Méthodes adaptatives pour l'optimisation dans un environnement stochastique

Florian Strub

Contributions à l'apprentissage séquentiel profond et à son application à l'interaction homme-robot

Kiewan Villatel

Sequential Learning for Online Advertising

Romain Warlop

Novel Learning and Exploration-Exploitation Methodes for Effective Recommender Systems 2018-10-19

Alexandre Berard

Neural Machine Translation Architectures and Applications 2018-06-15

Daniele Calandriello

Efficient Sequential Learning in Structured and Constrained Environments 2017-12-18

Julien Perolat

REINFORCEMENT LEARNING: THE MULTIPLAYER CASE 2017-12-18

Marc Abeille

Exploration-Exploitation with Thompson Sampling in Linear Systems 2017-12-13

Pratik Gajane

Multi-armed bandits with unconventional feedback 2017-11-14

Frédéric Guillou

On Recommendation Systems in Sequential Context 2016-12-02

Tomas Kocak

Sequential learning with similarities 2016-11-28

Vincenzo Musco

Usages of Graphs and Synthetic Data for Software Propagation Analysis 2016-11-03

Hadrien Glaude

Learning rational linear sequential systems using the method of moments 2016-07-08

Marta Soare

Computational and sample complexity of planning and reinforcement learning algorithms 2015-12-14

Amir Sani

Machine Learning for Decision-Making under Uncertainty 2015-05-12

Olivier Nicol

Data-driven evaluation of Contextual Bandit algorithms and applications to Dynamic Recommendation. 2014-12-18

Boris Baldassari

Maisqual : Amélioration de la qualité logicielle par fouille de données. 2014-07-01

Victor Gabillon

Budgeted Classification-based Policy Iteration 2014-06-12

Azadeh Khaleghi

Online Sequence Prediction 2013-11-18

Christophe Salperwyck

Apprentissage incrémental en ligne sur flux de données 2012-11-30

Alexandra Carpentier

De l'échantillonnage optimal en grande et petite dimension 2012-10-05

Jean Francois Hren

Compromis exploration - Exploitation en optimisation et contrôle 2012-06-01

Odalric-Ambrym Maillard

Apprentissage Séquentiel : Bandits, Statistique et Renforcement 2011-10-03

Manuel Loth

Algorithmes d'Ensembles Actifs pour le LASSO 2011-07-08

Sébastien Bubeck

Bandits Games and Clustering Foundations 2010-06-10

Michal Valko

Bandits and graphs and structures 2016-06-15

Jérémie Mary

Data-Driven Recommender Systems - Sequences of Recommendations 2015-11-24

Mohammad Ghavamzadeh

Complexité d’Échantillonnage pour la Prise de Décision Séquentielle 2014-06-11

Daniil Ryabko

Apprenabilité dans les problèmes de l'inférence séquentielle 2011-12-19

Other ' DatInG : Data Intelligence Group ' teams

LINKS MAGNET SIGMA