Previous | 
Home
Section: Partnerships and Cooperations
International Initiatives
Inria Associate Teams
SEQRL
Title: Decision-making under Uncertainty with Applications to Reinforcement Learning, Control, and Games
Website: http://sites.google.com/site/associateteamualberta/home
Abstract: This associate team aims at bridging researchers from the SequeL team-project at Inria Lille with the Department of Computing Science of the University of Alberta in Canada. Our common interest lies in machine learning, especially reinforcement learning, bandit algorithms and statistical learning with applications to control and computer games. The department of Computing Science at the University of Alberta is internationally renown as a leading research institute on these topics. The research work spans from theory to applications. Grounded on an already existing scientific collaboration, this associate team will make it easier to collaborate further between the two institutes, and thus strengthen this relationship. We foresee that the associate team will boost our collaboration, create new opportunities for financial support, and open-up a long-term fruitful collaboration between the two institutes. The collaboration will be through organizing workshops and exchanging researchers, postdoctoral fellows, and Ph.D. students between the two institutes.
Activity report: This year we had two Ph.D. students from the university of Alberta, Yasin Abbasi and Bernardo Avila Pires, who visited SequeL for six and four weeks, respectively. We send our Ph.D. student Amir Sani to a workshop organized by the university of Alberta and McGill university in Barbados in April. Mohammad Ghavamzadeh had a one week visit to the university of Alberta to work with Csaba Szepesvári and Bernardo Avila Pires.
Joint Publications: We have one conference paper submitted [53] and one in preparation [61] this year.
Inria International Partners
University of Alberta, Edmonton, Alberta, Canada.
Bernardo Avila Pires Collaborator
With Csaba Szepesvári we managed the associate team with the university of Alberta. We have had several visits to SequeL and UAlberta this year. We also have a conference paper [61] on risk bounds in cost-sensitive multiclass classification in preparation with Csaba Szepesvári and Bernardo Avila Pires.
McGill University, Montreal, Quebec, Canada.
Amir massoud Farahmand Collaborator
Mohammad Ghavamzadeh and Rémi Munos wrote a proposal with Joelle Pineau, Doina Precup, and Amir Farahmand to start an associate team with the McGill university. Mohammad Ghavamzadeh also have a conference paper submitted [53] on classification-based approximate policy iteration with Amir Farahmand and Doina Precup.
Technion - Israel Institute of Technology, Haifa, Israel.
Prof. Shie Mannor Collaborator
Mohammad Ghavamzadeh continued his collaboration with Shie Mannor. This year, we co-authored a book chapter on Bayesian reinforcement learning [57] .
University of Waterloo, Waterloo, Ontario, Canada.
Prof. Pascal Poupart Collaborator
Mohammad Ghavamzadeh continued his collaboration with Pascal Poupart. This year, we co-authored a book chapter on Bayesian reinforcement learning [57] .
-
Prof. Nicola Gatti Collaborator
We continued our collaboration on transfer in reinforcement learning and we developed a novel collaboration focused on the interplay between bandit theory and mechanism design, notably in the sponsored search auction application domain [35] .