Geodesic
Intelligent control system for road intersection
Problemy fiziki, matematiki i tehniki, no. 4 (2023), pp. 87-93.

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

An approach to the creation of intelligent object control systems using machine learning with reinforcement is illustrated using the example of an intersection control system. The simulation model of the intersection, chosen as the learning environment, is described. The results of a comparative analysis of the performance of various learning algorithms are presented. The results of applying the Monte Carlo policy gradient to train the intersection model are presented.
Keywords: transport network, reinforcement learning, neural networks, throughput, security, control systems, policy gradient. 
@article{PFMT_2023_4_a14,
     author = {E. I. Sukach and M. V. Biza},
     title = {Intelligent control system for road intersection},
     journal = {Problemy fiziki, matematiki i tehniki},
     pages = {87--93},
     publisher = {mathdoc},
     number = {4},
     year = {2023},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/PFMT_2023_4_a14/}
}
TY  - JOUR
AU  - E. I. Sukach
AU  - M. V. Biza
TI  - Intelligent control system for road intersection
JO  - Problemy fiziki, matematiki i tehniki
PY  - 2023
SP  - 87
EP  - 93
IS  - 4
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/PFMT_2023_4_a14/
LA  - ru
ID  - PFMT_2023_4_a14
ER  - 
%0 Journal Article
%A E. I. Sukach
%A M. V. Biza
%T Intelligent control system for road intersection
%J Problemy fiziki, matematiki i tehniki
%D 2023
%P 87-93
%N 4
%I mathdoc
%U http://geodesic.mathdoc.fr/item/PFMT_2023_4_a14/
%G ru
%F PFMT_2023_4_a14
E. I. Sukach; M. V. Biza. Intelligent control system for road intersection. Problemy fiziki, matematiki i tehniki, no. 4 (2023), pp. 87-93. http://geodesic.mathdoc.fr/item/PFMT_2023_4_a14/

[1] E.I. Sukach, V.N. Galushko, P.V. Giruts, “Primenenie imitatsionnykh modelei dlya prinyatiya reshenii v sistemakh upravleniya na transporte”, Matematicheskie mashiny i sistemy, 2010, no. 1, 185–192

[2] E.I. Sukach, “Metod pereraspredeleniya avtomobilnykh transportnykh potokov regiona na osnove imitatsionnogo modelirovaniya”, Reestratsiya, zberigannya i obrobka danikh (Data Recording, Storage Processing), 10:3 (2008), 37–45

[3] Yu.G. Karpov, Imitatsionnoe modelirovanie sistem. Vvedenie v modelirovanie s AnyLogic 5, BKhV-Peterburg, SPb., 2009, 390 pp.

[4] Richard S. Satton, Endryu Dzh. Barto, Obuchenie s podkrepleniem: vvedenie, per. s angl. A.A. Slinkina, 2-e izd., DMK Press, M., 2020, 552 pp.

[5] Ravichandiran Sudkharsan, Glubokoe obuchenie s podkrepleniem na Python. OpenAI Gym i TensorFlow dlya profi, Piter, SPb., 2019, 251 pp.

[6] Biblioteka dorozhnogo dvizheniya, (Data dostupa: 15.04.2023) https://www.anylogic.ru/

[7] M.V. Biza, E.I. Sukach, “Primenenie gradientov politiki v khode obucheniya s podkrepleniem”, Materialy KhI respublikanskoi nauchno-prakticheskoi konferentsii «Vychislitelnye metody, modeli i obrazovatelnye tekhnologii», Brestskii gosudarstvennyi universitet imeni A. S. Pushkina (22 oktyabrya 2022 g., Brest, 2022), 124–125