Geodesic
Applying reinforced learning for solving the problem of structuring the external environment
News of the Kabardin-Balkar scientific center of RAS, no. 6 (2020), pp. 14-19.

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

The paper is concerned with the problem of structuring the external environment. The proposed approach is based on a reinforcement learning method that trains a multi-agent neural network. A feature of the approach is that the structuring of environment is carried out by a team of robots that can interact with each other through messages. The formalized formulation of training problem is proposed.
Keywords: multiagent neural network, multiagent system, robotic systems, collective behavior. 
@article{IZKAB_2020_6_a1,
     author = {M. I. Anchekov},
     title = {Applying reinforced learning for solving the problem of structuring the external environment},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {14--19},
     publisher = {mathdoc},
     number = {6},
     year = {2020},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a1/}
}
TY  - JOUR
AU  - M. I. Anchekov
TI  - Applying reinforced learning for solving the problem of structuring the external environment
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2020
SP  - 14
EP  - 19
IS  - 6
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a1/
LA  - ru
ID  - IZKAB_2020_6_a1
ER  - 
%0 Journal Article
%A M. I. Anchekov
%T Applying reinforced learning for solving the problem of structuring the external environment
%J News of the Kabardin-Balkar scientific center of RAS
%D 2020
%P 14-19
%N 6
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a1/
%G ru
%F IZKAB_2020_6_a1
M. I. Anchekov. Applying reinforced learning for solving the problem of structuring the external environment. News of the Kabardin-Balkar scientific center of RAS, no. 6 (2020), pp. 14-19. http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a1/

[1] A. Aydemir, P. Jensfelt, J. Folkesson, “What can we learn from 38,000 rooms? Reasoning about unexplored space in indoor environments”, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2012, 4675–4682 | DOI

[2] M. Luperto, F. Amigoni, “Predicting the global structure of indoor environments: A constructive machine learning approach”, Autonomous Robots, 43:4 (2018), 813–835 | DOI

[3] C. Galindo, A. Saffiotti, S. Coradeschi, P. Buschka, J. A. Fernandez-Madrigal , J. Gonzalez, “Multi-hierarchical semantic maps for mobile robotics”, IEEE/RSJ International Conference on Intelligent Robots and Systems, Edmonton, Alta, 2005, 2278–2283

[4] P. F. Patel-Schneider, A. L. Resnick, D. L. McGuinness, E. Weixelbaum, M. Abrahams, A. Borgida, NeoClassic Reference Manual: Version 1.0. AT Labs Research, Artificial Intelligence Principles Research Department, 1996

[5] M. I. Anchokov, M. P. Krivenko, “Computer model of the emergence of collective behavior of robots”, News of the KBSC of RAS, 2019, no. 6 (92), 21–26

[6] R. S. Sutton, E. G. Barto, Reinforcement learning, Binom. Knowledge Laboratory, 2017, 399 pp.