Reference : Neuromorphic reinforcement learning
Scientific congresses and symposiums : Unpublished conference
Engineering, computing & technology : Electrical & electronics engineering
Engineering, computing & technology : Multidisciplinary, general & others
http://hdl.handle.net/2268/115753
Neuromorphic reinforcement learning
English
Dethier, Julie mailto [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Ernst, Damien [> >]
Sepulchre, Rodolphe [> >]
29-Mar-2012
No
International
31st Benelux Meeting on Systems and Control
March 27-29, 2012
Heijen/Nijmegen
The Netherlands
[en] Living organisms are able to successfully perform challeng- ing tasks such as perception, classification, association, and control. In hope for similar successes in artificial systems, neuromorphic engineering uses neurophysiological models of perception and information processing in biological sys- tems to emulate their functions but also resemble their struc- ture [1]. In this abstract, we focus on the basal ganglia (BG), brain region in control of primitive functions of the nervous system, and specifically on their involvement in action selec- tion and reinforcement learning (RL). We hypothesize that neuromorphic-inspired systems will greatly benefit the RL community.
Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
http://hdl.handle.net/2268/115753

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Neuromorphic reinforcement learning.pdfAuthor preprint55.12 kBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.