Remi Munos

 Currently on leave ("détachement") at Microsoft Research New-England

Senior Researcher (DR2)
INRIA Lille - Nord Europe, SequeL team (Sequential Learning)


 Publications


 Teaching (Master Maths Vision Apprentissage ENS Cachan)


Research interests:

Bandit theory

KL-UCB, UCB-V, Thompson sampling, many-armed bandits

Foundations of Monte-Carlo Tree Search

Optimistic optimization, optimistic planning

Random projections

For Least Squares regression and Reinforcement Learning

Reinforcement Learning (RL) and approximate dynamic programming (DP)

Finite-time analysis of RL and DP (Lasso-TD, LSTD, AVI, API, BRM, compressed-LSTD)

RL and DP with function approximation (Lp analysis)

Reinforcement Learning and optimal control in continuous time

Numerical solutions to HJB equations

Stability analysis via viscosity solutions

Variable resolution discretizations

Policy gradient in RL and control

Sensitivity analysis in continuous time

Sensitivity analysis in POMDPs via particle filters



 Videos


Projects and activities:

Scientific events


PhD Students:


Contact:

Address:
Rémi Munos, SEQUEL project, INRIA Lille - Nord Europe,
40 avenue Halley, 59650 Villeneuve d'Ascq, FRANCE

Email: remi (dot) munos (at) inria (dot) fr
Tel: (0 or 33)3 59 57 79 06
Fax: (0 or 33)3 59 57 78 50