Connectionists: Post-Doctoral position at INRIA, Lille, France

[Davy Manuel]

One year post-doctoral position in the INRIA-Sequel research group,
Lille, France

Scientific context :

This project is at the heart of SequeL's research interest, namely
'sequential learning'. There are many situations where one collects data
from which actions should be decided sequentially. For example, a
mobile robot collects measurement from its environment thanks to several
sensors, and must decide where to go, based on these measurements. When
the robot resources  (energy, sensor availability, time)  are limited,
the sensors must be managed so as to reduce some cost. This project will
focus on this task, within the general assumption that the environment
is not perfectly known, and that the sensor behavior may be known only
partly.

Description of the post-doc activities :

The post-doctoral researcher will need to develop and implement
reinforcement learning as well as particle filtering algorithms to
achieve these tasks, within  the general framework of Partially
Observable Markov Decision Processes (POMDPs). These developments will
be made in the context of a real application. The approaches that prove
successful in simulations will be implemented onto real robots.

Applicant's required skills

The applicant needs to have a PhD with a focus on either particle
filtering or reinforcement learning.

Person to contact for further informations : Manuel Davy
(Manuel.Davy at inria.fr)

To apply for, please send a CV and a covering letter to :
Chantal.birot at inria.fr and Nathalie.legoullon at inria.fr

-------------------------------------------------------
Sequel's url is
http://www.grappa.univ-lille3.fr/cgi-bin/twiki/view/Sequel


This add may also be found at the url
http://www-futurs.inria.fr/emplois/fiches_post_doc/Fiche_SequeL_Ang.html


Please be aware that conditions apply, see
http://www-futurs.inria.fr/emplois/Offers_for_Post.html
---------------------------------------------------------