Applicants are invited for an up to 6 months internship at INRIA Lille – Team Sequel working with Remi Munos and Mohammad Ghavamzadeh.
This is a joint project with Shie Mannor at Technion in Haifa, Israel, and is funded by PASCAL2 European Network of Excellence. The project is carried out at INRIA Lille within the SequeL team with the opportunity to visit Shie Mannor’s team at Technion.
The goal of this project is to devise, analyze, implement, and experiment with alternative approaches to reinforcement learning when
the dimension of the input space is large and possibly infinite. We would like to investigate the possibility of using the recent results
in sparse representations using L1-regularization and random projections in reinforcement learning.
Candidates must have either a Masters degree or be in the last stage of their Masters program in machine learning, statistics, or related
fields, with ideally some background in reinforcement learning, kernel methods, sparse methods, and optimization.
After the internship, there would be a possibility for the student to pursue a Ph.D. program at INRIA Lille – Team SequeL.
Candidates should send a detailed CV to Remi Munos (remi.munos at inria.fr) and Mohammad Ghavamzadeh (mohammad.ghavamzadeh at inria.fr).