Geodesic
Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment
Russian journal of nonlinear dynamics, Tome 7 (2011) no. 4, pp. 859-875

Voir la notice de l'article provenant de la source Math-Net.Ru

Method of reinforcement learning of spiking neural network that controls robot or virtual agent is described. Using spiking neurons as key elements of a network allows us to exploit spatial and temporal structure of input sensory information. Teaching of the network is implemented with a use of reinforcement signals that come from the external environment and reflect the success of agents recent actions. A maximization of the received reinforcement is done via modulated minimization of neurons informational entropy that depends on neurons weights. The laws of weights changes were close to modulated synaptic plasticity that was observed in real neurons. Reinforcement learning algorithm was tested on a task of a resource search in a virtual discrete environment.
Keywords: spiking neuron, adaptive control, reinforcement learning, informational entropy. 
@article{ND_2011_7_4_a8,
     author = {O. Yu. Sinyavskiy and A. I. Kobrin},
     title = {Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment},
     journal = {Russian journal of nonlinear dynamics},
     pages = {859--875},
     publisher = {mathdoc},
     volume = {7},
     number = {4},
     year = {2011},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ND_2011_7_4_a8/}
}
TY  - JOUR
AU  - O. Yu. Sinyavskiy
AU  - A. I. Kobrin
TI  - Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment
JO  - Russian journal of nonlinear dynamics
PY  - 2011
SP  - 859
EP  - 875
VL  - 7
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/ND_2011_7_4_a8/
LA  - ru
ID  - ND_2011_7_4_a8
ER  - 
%0 Journal Article
%A O. Yu. Sinyavskiy
%A A. I. Kobrin
%T Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment
%J Russian journal of nonlinear dynamics
%D 2011
%P 859-875
%V 7
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/ND_2011_7_4_a8/
%G ru
%F ND_2011_7_4_a8
O. Yu. Sinyavskiy; A. I. Kobrin. Reinforcement learning of a spiking neural network in the task of control of an agent in a virtual discrete environment. Russian journal of nonlinear dynamics, Tome 7 (2011) no. 4, pp. 859-875. http://geodesic.mathdoc.fr/item/ND_2011_7_4_a8/