Machine Learning-Robotics
- Domaine
- Machine Learning-Robotics
- Domain - extra
- Reinforcement Learning
- Année
- 2011
- Starting
- Sept. 2011
- État
- Open
- Sujet
- Integrity Preserving Policy Learning
- Thesis advisor
- SEBAG Michèle
- Co-advisors
- LAVIOLETTE Francois, Université de Laval, Québec
- Laboratory
- Collaborations
- Abstract
- Robotic policy learning in-situ requires specific strategies in order to preserve the robot physical integrity during the exploration of its environment.
The goal of the PhD is to propose such strategies, define and establish some PAC guarantees about the incurred risk and experimentally investigate their performance.
- Context
- Objectives
- Work program
- Extra information
- Prerequisite
- Background in Maths and Statistics
Programming skills - Détails
IPRL.pdf- Expected funding
- Institutional funding
- Status of funding
- Expected
- Candidates
- Nicolas Galichet
- Utilisateur
- michele-martine.sebag
- Créé
- Dimanche 19 juin 2011 17:55:54 CEST
- dernière modif.
- Dimanche 19 juin 2011 17:55:54 CEST
Connexion
Ecole Doctorale Informatique Paris-Sud
Directrice
Nicole Bidoit
Assistante
Stéphanie Druetta
Conseiller aux thèses
Dominique Gouyou-Beauchamps
ED 427 - Université Paris-Sud
UFR Sciences Orsay
Bat 650 - aile nord - 417
Tel : 01 69 15 63 19
Fax : 01 69 15 63 87
courriel: ed-info à lri.fr