Geodesic
Development of a simulation model for predicting the behavior of an intelligent agent based on an invariant of a recursive
News of the Kabardin-Balkar scientific center of RAS, no. 6 (2020), pp. 80-90.

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

The active development of self-organizing decision-making and control systems based on the multi-agent approach has led to the fact that the concept of an intelligent agent is one of the main in the field of artificial intelligence. The paper presents the formalism of an intelligent agent based on multi-agent neurocognitive architectures. An intelligent agent is understood as an intelligent system based on a multi-agent neurocognitive architecture, which consists of software agents-neurons, the behavior of which is determined by an internal objective function, the implementation of which is carried out due to the ability of agents to interact with each other. An algorithm for learning an intelligent agent based on self-organization of an invariant of multi-agent neurocognitive architectures according to a scenario for predicting eating behavior is presented. Learning based on the actual scenario of behavior allows the AI to predict and, in a preventive manner, prevent a decrease in its own energy to a critical value, signal the onset of hunger and satiety. A simulation model of scenario prediction of the eating behavior of an intelligent agent based on an invariant of a multi-agent neurocognitive architecture has been developed. The use of rational software agents for modeling neural-like elements and organizing their multi-agent interaction in the process of teaching neurocognitive architecture based on the formation of axodendronal connections as part of control functional systems determines the scientific novelty of the result. Further development of the presented work is associated with teaching an intelligent agent more complex exploratory behavior.
Keywords: simulation modeling, multi-agent systems, neurocognitive architectures, self-learning systems.
Mots-clés : intelligent agent 
@article{IZKAB_2020_6_a7,
     author = {I. A. Pshenokova and Z. A. Sundukov},
     title = {Development of a simulation model for predicting the behavior of an intelligent agent based on an invariant of a recursive},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {80--90},
     publisher = {mathdoc},
     number = {6},
     year = {2020},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a7/}
}
TY  - JOUR
AU  - I. A. Pshenokova
AU  - Z. A. Sundukov
TI  - Development of a simulation model for predicting the behavior of an intelligent agent based on an invariant of a recursive
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2020
SP  - 80
EP  - 90
IS  - 6
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a7/
LA  - ru
ID  - IZKAB_2020_6_a7
ER  - 
%0 Journal Article
%A I. A. Pshenokova
%A Z. A. Sundukov
%T Development of a simulation model for predicting the behavior of an intelligent agent based on an invariant of a recursive
%J News of the Kabardin-Balkar scientific center of RAS
%D 2020
%P 80-90
%N 6
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a7/
%G ru
%F IZKAB_2020_6_a7
I. A. Pshenokova; Z. A. Sundukov. Development of a simulation model for predicting the behavior of an intelligent agent based on an invariant of a recursive. News of the Kabardin-Balkar scientific center of RAS, no. 6 (2020), pp. 80-90. http://geodesic.mathdoc.fr/item/IZKAB_2020_6_a7/

[1] Russel Stuart, Peter Norvig, Artificial Intelligence: A Modern Approach, 2nd ed., Prentice Hall, Upper Saddle River, New Jersey:, 2003

[2] Dzh. K. Lafta, Teoriya organizatsii, ucheb. pos., Velbi: Prospekt, M., 2003, 416 pp.

[3] Z. Nagoev, O. Nagoeva, I. Gurtueva, “Multi-agent neurocognitive models of semantics of spatial localization of events”, Cognitive Systems Research, 59 (2020), 91–102 | DOI

[4] Z. Nagoev, I. Pshenokova, I. Gurtueva, K. Bzhikhatlov, “A Simulation Model for the Cogni-tive Function of Static Objects Recognition Based on Machine-Learning Multi-Agent Architec-tures”, Advances in Intelligent Systems and Computing, 948, 370–379 | DOI

[5] Z. V. Nagoev, Intellectics or thinking in living and artificial systems, Publishing House of KBSC RAS, Nalchik, 2013, 213 pp.

[6] I. A. Pshenokova, O. V. Nagoeva, I. A. Gurtueva, A. Ayran, “Algorithm for learning an intelligent decision-making system based on multi-agent neurocogni-tive architectures”, News of the Kabardino-Balkarian Scientific Center of RAS, 2020, no. 3 (95), 23–31

[7] V. V. Shulgovsky, Fundamentals of Neurophysiology, Tutorial, Aspect Press, M., 2002, 277 pp.

[8] Z. V. Nagoev, Z. A. Sundukov, I. A. Pshenokova, V. A. Denisenko, “The architecture of the CAD of distributed artificial intelligence based on self-organizing neurocognitive architectures”, News of the Kabardino-Balkarian Scientific Center of RAS, 2020, no. 2 (94), 40–47