Reference : Introducing neuromodulation in deep neural networks to learn adaptive behaviours
E-prints/Working papers : Already available on another site
Engineering, computing & technology : Computer science
http://hdl.handle.net/2268/230984
Introducing neuromodulation in deep neural networks to learn adaptive behaviours
English
Vecoven, Nicolas mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data >]
Ernst, Damien mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Smart grids >]
Wehenkel, Antoine mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Big Data >]
Drion, Guillaume mailto [Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
3-Jan-2019
62
No
[en] reinforcement learning ; neural nets ; neuromodulation ; deep learning
[en] In this paper, we propose a new deep neural network architecture, called NMD net, that has been specifically designed to learn adaptive behaviours. This architecture exploits a biological mechanism called neuromodulation that sustains adaptation in biological organisms. This architecture has been introduced in a deep-reinforcement learning architecture for interacting with Markov decision processes in a meta-reinforcement learning setting where the action space is continuous. The deep-reinforcement learning architecture is trained using an advantage actor-critic algorithm. Experiments are carried on several test problems. Results show that the neural network architecture with neuromodulation provides significantly better results than state-of-the-art recurrent neural networks which do not exploit this mechanism.
Researchers ; Professionals ; Students
http://hdl.handle.net/2268/230984
https://arxiv.org/abs/1812.09113

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
deep-RL-neuromodulation.pdfPublisher postprint5.5 MBView/Open

Bookmark and Share SFX Query

All documents in ORBi are protected by a user license.