<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">trudyniisi</journal-id><journal-title-group><journal-title xml:lang="ru">Труды НИИСИ</journal-title><trans-title-group xml:lang="en"><trans-title>SRISA Proceedings</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2225-7349</issn><issn pub-type="epub">3033-6422</issn><publisher><publisher-name>НИЦ «КУРЧАТОВСКИЙ ИНСТИТУТ» - НИИСИ</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.25682/NIISI.2025.1.0009</article-id><article-id custom-type="elpub" pub-id-type="custom">trudyniisi-7</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ И МАШИННОЕ ОБУЧЕНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING</subject></subj-group></article-categories><title-group><article-title>Модель обороны коллектива слабых мирных  агентов от сильного агента-хищника</article-title><trans-title-group xml:lang="en"><trans-title>Modeling the Defense of Weak Prey Agents  Against a Strong Predator Agent</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Редько</surname><given-names>В. Г.</given-names></name><name name-style="western" xml:lang="en"><surname>Red’ko</surname><given-names>V. G.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Москва</p></bio><email xlink:type="simple">vgredko@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>НИЦ «КУРЧАТОВСКИЙ ИНСТИТУТ» — НИИСИ</institution></aff><aff xml:lang="en"><institution>NRC "Kurchatov Institute" — SRISA</institution></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>29</day><month>09</month><year>2025</year></pub-date><volume>15</volume><issue>1</issue><issue-title>МАТЕМАТИЧЕСКОЕ И КОМПЬЮТЕРНОЕ МОДЕЛИРОВАНИЕ СЛОЖНЫХ СИСТЕМ:  ТЕОРЕТИЧЕСКИЕ И ПРИКЛАДНЫЕ АСПЕКТЫ</issue-title><fpage>65</fpage><lpage>71</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Редько В.Г., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Редько В.Г.</copyright-holder><copyright-holder xml:lang="en">Red’ko V.G.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.t-niisi.ru/jour/article/view/7">https://www.t-niisi.ru/jour/article/view/7</self-uri><abstract><p>Построена и изучена модель взаимодействия сообщества относительно слабых мирных агентов в клеточном мире с сильным агентом-хищником. Агент-хищник может нападать на мирных агентов, убивать и съедать их. Внутренняя система управления мирного агента представляет собой нейронную сеть. Имеются две стратегии мирных агентов: 1) обычная мирная жизнь, 2) оборона от сильного агента-хищника. В первой стратегии мирные агенты выполняют следующие действия: находиться в состоянии покоя, питаться, размножаться, перемещаться по миру. Во второй стратегии действия мирных агентов таковы: уход от агента хищника, угроза агенту-хищнику, нападение на агента-хищника. Выходами нейронной сети являются сигналы, определяющие действия мирного агента. Агент-хищник выполнять следующие действия: находиться в состоянии покоя, уходить от угрожающих мирных агентов, нападать на мирных агентов. Повеление агента-хищника определяется простыми логическими правилами. Анализ модели производился путем компьютерного моделирования. Показано, что при достаточно естественном выборе параметров модели коллектив мирных агентов побеждает агента-хищника, а именно, с течением времени ресурс мирных агентов уверенно растёт, а ресурс агента-хищника в итоге уменьшается до нуля, т.е. агент-хищник погибает. Также продемонстрировано, что для обеспечения способности к такой обороне, мирным агентам нужно достаточно большое количество пищи. При малом количестве пищи мирных агентов агент-хищник подавляет мирных агентов. </p></abstract><trans-abstract xml:lang="en"><p>We constructed and studied a model of interaction between a community of relatively weak prey  agents and a strong predator agent in a two‑dimensional grid world (a lattice environment typical of grid automata and agent-based models). The predator can attack, kill, and consume prey agents. Each prey agent is controlled by a neural network and adopts one of two behavioral strategies: (1) normal activity, or (2) defense against the predator. In the normal activity strategy, prey agents lie dormant, feed, breed, and move through the grid. In the defense strategy, they attempt to escape, threaten, or attack the predator. The neural network outputs control each agent’s ac tions. The predator follows a simpler, rule-based protocol: it can lie dormant, evade threatening prey, or attack them. Its behavior is governed by basic logic. We analyzed the model using computer simulations. We found that, with realistic parameters, the prey agents collectively overcome the predator: prey resource levels increase steadily, while the predator’s resources decline to zero, leading to its extinction. We also discovered that successful defense requires a sufficiently abundant food supply; when prey food is scarce, the predator successfully suppresses the prey population. We used computer simulation to analyze the model. When the prey agents’ food supply is low, the predator agent suppresses the prey agents. </p></trans-abstract><kwd-group xml:lang="ru"><kwd>мирные агенты</kwd><kwd>агент-хищник</kwd><kwd>борьба между агентами</kwd></kwd-group><kwd-group xml:lang="en"><kwd>prey agents</kwd><kwd>predatory agent</kwd><kwd>prey-predator struggle</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">C.G. Langton (ed.). Artificial Life: The Proceedings of an Interdisciplinary Workshop on the Synthe sis and Simulation of Living Systems. Redwood City CA: Addison-Wesley, 1989.</mixed-citation><mixed-citation xml:lang="en">C.G. Langton (ed.). Artificial Life: The Proceedings of an Interdisciplinary Workshop on the Synthe sis and Simulation of Living Systems. Redwood City CA: Addison-Wesley, 1989.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">C.G. Langton, C. Taylor, J.D. Farmer, S. Rasmussen (eds.). Artificial Life II: Proceedings of the Second Artificial Life Workshop. Redwood City CA: Addison-Wesley, 1992.</mixed-citation><mixed-citation xml:lang="en">C.G. Langton, C. Taylor, J.D. Farmer, S. Rasmussen (eds.). Artificial Life II: Proceedings of the Second Artificial Life Workshop. Redwood City CA: Addison-Wesley, 1992.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">L.S. Yaeger. Computational genetics, physiology, metabolism, neural systems, learning, vision, and behavior or PolyWorld: Life in a new context. In: C.G. Langton (Ed.). Proceedings of the Artificial Life III Conference. Reading, Mass.: Addison-Wesley, 1994, 263–298.</mixed-citation><mixed-citation xml:lang="en">L.S. Yaeger. Computational genetics, physiology, metabolism, neural systems, learning, vision, and behavior or PolyWorld: Life in a new context. In: C.G. Langton (Ed.). Proceedings of the Artificial Life III Conference. Reading, Mass.: Addison-Wesley, 1994, 263–298.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">D. Ackley, M. Littman. Interactions between learning and evolution. In [2], 487–509.</mixed-citation><mixed-citation xml:lang="en">D. Ackley, M. Littman. Interactions between learning and evolution. In [2], 487–509.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">M. Burtsev, P. Turchin. Evolution of cooperative strategies from first principles. “Nature”, V. 440 (2006), No. 7087, 1041–1044.</mixed-citation><mixed-citation xml:lang="en">M. Burtsev, P. Turchin. Evolution of cooperative strategies from first principles. “Nature”, V. 440 (2006), No. 7087, 1041–1044.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">K. Lorenz. On Aggression. London, New York, Routledge Classics, 2002.</mixed-citation><mixed-citation xml:lang="en">K. Lorenz. On Aggression. London, New York, Routledge Classics, 2002.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">V.G. Red’ko. Model of collective interaction in competing groups of autonomous agents. In: V. Redko, D. Yudin, W. Dunin-Barkowski, B. Kryzhanovsky, Y. Tiumentsev (eds). Advances in Neural Com putation, Machine Learning, and Cognitive Research VIII. NI 2024. Studies in Computational Intelligence, V. 1179, Springer, Cham, 2025, 345–352.</mixed-citation><mixed-citation xml:lang="en">V.G. Red’ko. Model of collective interaction in competing groups of autonomous agents. In: V. Redko, D. Yudin, W. Dunin-Barkowski, B. Kryzhanovsky, Y. Tiumentsev (eds). Advances in Neural Com putation, Machine Learning, and Cognitive Research VIII. NI 2024. Studies in Computational Intelligence, V. 1179, Springer, Cham, 2025, 345–352.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">M.A. Semenov, D.A. Terkel. Об эволюции механизмов изменчивости посредством косвенного отбора. Journal of General Biology, Vol. 46 (1985), No. 2, pp. s271–277.</mixed-citation><mixed-citation xml:lang="en">M.A. Semenov, D.A. Terkel. Об эволюции механизмов изменчивости посредством косвенного отбора. Journal of General Biology, Vol. 46 (1985), No. 2, pp. s271–277.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Red’ko V.G A Model of Interaction and Competition Between Two Types of Autonomous Agents. Russian Journal of Cybernetics. Vol. 6 (2025), No. 1, pp. 128–136.</mixed-citation><mixed-citation xml:lang="en">Red’ko V.G A Model of Interaction and Competition Between Two Types of Autonomous Agents. Russian Journal of Cybernetics. Vol. 6 (2025), No. 1, pp. 128–136.</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
