<?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">vavilov</journal-id><journal-title-group><journal-title xml:lang="ru">Вавиловский журнал генетики и селекции</journal-title><trans-title-group xml:lang="en"><trans-title>Vavilov Journal of Genetics and Breeding</trans-title></trans-title-group></journal-title-group><issn pub-type="epub">2500-3259</issn><publisher><publisher-name>Institute of Cytology and Genetics of Siberian Branch of the RAS</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18699/vjgb-25-110</article-id><article-id custom-type="elpub" pub-id-type="custom">vavilov-4888</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>СИСТЕМНАЯ КОМПЬЮТЕРНАЯ БИОЛОГИЯ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>SYSTEMS COMPUTATIONAL BIOLOGY</subject></subj-group></article-categories><title-group><article-title>Самообучающиеся виртуальные организмы в физическом симуляторе: об оптимальном разрешении их зрительной системы, архитектуре нервной системы и вычислительной сложности задачи</article-title><trans-title-group xml:lang="en"><trans-title>Self-learning virtual organisms in a physics simulator: on the optimal resolution of their visual system, the architecture of the nervous system and the computational complexity of the problem</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>Зенин</surname><given-names>М. С.</given-names></name><name name-style="western" xml:lang="en"><surname>Zenin</surname><given-names>M. S.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новосибирск</p></bio><bio xml:lang="en"><p>Novosibirsk</p></bio><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Девятериков</surname><given-names>А. П.</given-names></name><name name-style="western" xml:lang="en"><surname>Devyaterikov</surname><given-names>A. P.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новосибирск</p></bio><bio xml:lang="en"><p>Novosibirsk</p></bio><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0003-1108-1486</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Пальянов</surname><given-names>А. Ю.</given-names></name><name name-style="western" xml:lang="en"><surname>Palyanov</surname><given-names>A. Yu.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Новосибирск</p></bio><bio xml:lang="en"><p>Novosibirsk</p></bio><email xlink:type="simple">palyanov@iis.nsk.su</email><xref ref-type="aff" rid="aff-3"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru">Новосибирский национальный исследовательский государственный университет<country>Россия</country></aff><aff xml:lang="en">Novosibirsk State University<country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru">Институт систем информатики им. А.П. Ершова Сибирского отделения Российской академии наук<country>Россия</country></aff><aff xml:lang="en">A.P. Ershov Institute of Informatics Systems of the Siberian Branch of the Russian Academy of Sciences<country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-3"><aff xml:lang="ru">Новосибирский национальный исследовательский государственный университет; Институт систем информатики им. А.П. Ершова Сибирского отделения Российской академии наук<country>Россия</country></aff><aff xml:lang="en">Novosibirsk State University; A.P. Ershov Institute of Informatics Systems of the Siberian Branch of the Russian Academy of Sciences<country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>12</day><month>12</month><year>2025</year></pub-date><volume>29</volume><issue>7</issue><fpage>1051</fpage><lpage>1061</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Зенин М.С., Девятериков А.П., Пальянов А.Ю., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Зенин М.С., Девятериков А.П., Пальянов А.Ю.</copyright-holder><copyright-holder xml:lang="en">Zenin M.S., Devyaterikov A.P., Palyanov A.Y.</copyright-holder><license 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://vavilov.elpub.ru/jour/article/view/4888">https://vavilov.elpub.ru/jour/article/view/4888</self-uri><abstract><p>   Зрение играет ключевую роль в жизни множества различных организмов, обеспечивая ориентацию в пространстве, поиск пищи, избегание хищников и социальное взаимодействие. У видов с относительно простой зрительной системой, таких как насекомые, эффективная поведенческая стратегия достигается за счет высокой специализации нейронов, адаптации к конкретным условиям среды, а также благодаря дополнительным сенсорным системам – обонянию или слуху. У животных с более сложным зрением и нервной системой, таких как млекопитающие, когнитивные возможности и способности к адаптации значительно выше, однако выше и энергозатраты на работу мозга. Моделирование особенностей таких систем в виртуальной среде позволило бы исследовать фундаментальные принципы функционирования и обучения когнитивных систем, включая механизмы восприятия, памяти, принятия решений и их взаимодействие.</p><p>   В данной работе объектом исследования являются виртуальные организмы, обладающие зрительной системой и функционирующие в трехмерной физической среде на базе Unity ML-Agents – одного из наиболее высокопроизводительных современных симуляторов.</p><p>   Предложенная иерархическая архитектура управления, разделяющая когнитивные задачи между двумя модулями – зрительного восприятия/принятия решений и управления координированным движением конечностей для перемещения в физической среде – показала существенно большую скорость и эффективность обучения по сравнению с единой системой. Проведена серия численных экспериментов, направленных на выявление влияния параметров зрительной системы, конфигурации среды и архитектурных особенностей агентов на успешность их обучения с подкреплением (алгоритм PPO). Показано, что существует диапазон разрешений, обеспечивающий компромисс между вычислительной сложностью и успешностью выполнения задачи, а избыточная размерность сенсорных входных данных или пространства действий приводит к замедлению обучения. Должное внимание уделено также оценке вычислительной сложности системы и профилированию производительности ее основных компонентов. Полученные результаты представляют потенциальный интерес в контексте исследований искусственных агентов, вдохновленных биологическими системами эволюционного моделирования, включая нейроэволюционные подходы для создания более адаптивных и умных агентов и изучения когнитивных процессов в них.</p></abstract><trans-abstract xml:lang="en"><p>   Vision plays a key role in the lives of various organisms, enabling spatial orientation, foraging, predator avoidance and social interaction. In species with relatively simple visual systems, such as insects, effective behavioral strategies are achieved through high neural specialization, adaptation to specific environmental conditions, and the use of additional sensory systems such as olfaction or hearing. Animals with more complex vision and nervous systems, such as mammals, have greater cognitive abilities and flexibility, but this comes with increased demands on the brain’s energy costs and computational resources. Modeling the features of such systems in a virtual environment could allow researchers to explore the fundamental principles of sensorimotor integration and the limits of cognitive complexity, as well as test hypotheses about the interaction between perception, memory and decision-making mechanisms.</p><p>   In this work, we implement and investigate a model of virtual organisms with a visual system operating in a three-dimensional physical environment using the Unity ML-Agents software – one of the most high-performance simulation platforms currently available.</p><p>   We propose a hierarchical control architecture that separates locomotion and navigation tasks between two modules: (1) visual perception and decision-making, and (2) coordinated control of limb movement for locomotion in the physical environment. A series of numerical experiments was conducted to examine the influence of visual system parameters (e. g, resolution of the “first-person” view), environmental configuration and agent architectural features on the efficiency and outcomes of reinforcement learning (using the PPO algorithm). The results demonstrate the existence of an optimal range of resolutions that provide a trade-off between computational complexity and success in accomplishing the task, while excessive dimensionality of sensory inputs or action space leads to slower learning. We performed system performance profiling and identified key bottlenecks in large-scale simulations. The discussion considers biological parallels, highlighting cases of high behavioral efficiency in insects with relatively low-resolution visual systems, and the potential of neuroevolutionary approaches for adapting agent architectures. The proposed approach and the results obtained are of potential interest to researchers working on biologically inspired artificial agents, evolutionary modeling, and the study of cognitive processes in artificial systems.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>виртуальный организм</kwd><kwd>компьютерное моделирование</kwd><kwd>вычислительная сложность</kwd><kwd>зрительная система</kwd><kwd>нейронная сеть</kwd><kwd>симулятор</kwd><kwd>PPO</kwd><kwd>обучение с подкреплением</kwd><kwd>Unity ML-Agents</kwd></kwd-group><kwd-group xml:lang="en"><kwd>virtual organism</kwd><kwd>computational modeling</kwd><kwd>computational complexity</kwd><kwd>vision system</kwd><kwd>neural network</kwd><kwd>simulator</kwd><kwd>PPO</kwd><kwd>reinforcement learning</kwd><kwd>Unity ML-Agents</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">Aksoy V., Camlitepe Y. Spectral sensitivities of ants – a review. Anim Biol. 2018;68(1):55­73. doi: 10.1163/15707563­17000119</mixed-citation><mixed-citation xml:lang="en">Aksoy V., Camlitepe Y. Spectral sensitivities of ants – a review. Anim Biol. 2018;68(1):55­73. doi: 10.1163/15707563­17000119</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Attwell D., Laughlin S.B. An energy budget for signaling in the grey matter of the brain. J Cereb Blood Flow Metab. 2001;21(10):1133­-1145. doi: 10.1097/00004647­200110000­0000</mixed-citation><mixed-citation xml:lang="en">Attwell D., Laughlin S.B. An energy budget for signaling in the grey matter of the brain. J Cereb Blood Flow Metab. 2001;21(10):1133­-1145. doi: 10.1097/00004647­200110000­0000</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Bongard J.C. Evolutionary robotics. Commun ACM. 2013;56(8): 74­83. doi: 10.1145/2493883</mixed-citation><mixed-citation xml:lang="en">Bongard J.C. Evolutionary robotics. Commun ACM. 2013;56(8): 74­83. doi: 10.1145/2493883</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Botvinick M., Wang J.X., Dabney W., Miller K.J., Kurth-Nelson Z. Deep reinforcement learning and its neuroscientific implications. Neuron. 2020;107(4):603­616. doi: 10.1016/j.neuron.2020.06.014</mixed-citation><mixed-citation xml:lang="en">Botvinick M., Wang J.X., Dabney W., Miller K.J., Kurth-Nelson Z. Deep reinforcement learning and its neuroscientific implications. Neuron. 2020;107(4):603­616. doi: 10.1016/j.neuron.2020.06.014</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Cammaerts M.C. The visual perception of the ant Myrmica ruginodis (Hymenoptera: Formicidae). Biologia. 2012;67(6):1165­1174. doi: 10.2478/s11756­012­0112­z</mixed-citation><mixed-citation xml:lang="en">Cammaerts M.C. The visual perception of the ant Myrmica ruginodis (Hymenoptera: Formicidae). Biologia. 2012;67(6):1165­1174. doi: 10.2478/s11756­012­0112­z</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Cammaerts M.­C.T., Cammaerts R. Are ants (Hymenoptera, Formicidae) capable of self recognition? J Sci. 2015;5(7):521­532</mixed-citation><mixed-citation xml:lang="en">Cammaerts M.­C.T., Cammaerts R. Are ants (Hymenoptera, Formicidae) capable of self recognition? J Sci. 2015;5(7):521­532</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Chittka L., Muller H. Learning, specialization, efficiency and task allocation in social insects. Commun Integr Biol. 2009;2(2):151­154. doi: 10.4161/cib.7600</mixed-citation><mixed-citation xml:lang="en">Chittka L., Muller H. Learning, specialization, efficiency and task allocation in social insects. Commun Integr Biol. 2009;2(2):151­154. doi: 10.4161/cib.7600</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Chittka L., Niven J. Are bigger brains better? Curr Biol. 2009;19(21): R995­R1008. doi: 10.1016/j.cub.2009.08.023</mixed-citation><mixed-citation xml:lang="en">Chittka L., Niven J. Are bigger brains better? Curr Biol. 2009;19(21): R995­R1008. doi: 10.1016/j.cub.2009.08.023</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Devyaterikov А.P., Palyanov А.Y. A software system for modeling evolution in a population of organisms with vision, interacting with each other in 3D simulator. Vavilov J Genet Breed. 2022;26(8): 780­786. doi: 10.18699/VJGB­22­94</mixed-citation><mixed-citation xml:lang="en">Devyaterikov А.P., Palyanov А.Y. A software system for modeling evolution in a population of organisms with vision, interacting with each other in 3D simulator. Vavilov J Genet Breed. 2022;26(8): 780­786. doi: 10.18699/VJGB­22­94</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Hassabis D., Humaran D., Summerfield C., Botvinick M. Neuroscience-inspired artificial intelligence. Neuron. 2017;95(2):245­258. doi: 10.1016/j.neuron.2017.06.011</mixed-citation><mixed-citation xml:lang="en">Hassabis D., Humaran D., Summerfield C., Botvinick M. Neuroscience-inspired artificial intelligence. Neuron. 2017;95(2):245­258. doi: 10.1016/j.neuron.2017.06.011</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Juliani A., Berges V.­P., Teng E., Cohen A., Harper J., Elion C., Goy C., Gao Y., Henry H., Matter M., Lange D. Unity: A general platform for intelligent agents. arXiv. 2018. doi: 10.48550/arXiv.1809.02627</mixed-citation><mixed-citation xml:lang="en">Juliani A., Berges V.­P., Teng E., Cohen A., Harper J., Elion C., Goy C., Gao Y., Henry H., Matter M., Lange D. Unity: A general platform for intelligent agents. arXiv. 2018. doi: 10.48550/arXiv.1809.02627</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Land M.F., Nilsson D.­E. Animal Eyes. Oxford University Press, 2012. Available: https://www.softouch.on.ca/kb/data/Animal%20Eyes.pdf</mixed-citation><mixed-citation xml:lang="en">Land M.F., Nilsson D.­E. Animal Eyes. Oxford University Press, 2012. Available: https://www.softouch.on.ca/kb/data/Animal%20Eyes.pdf</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Menzel R. The honeybee as a model for understanding the basis of cognition. Nat Rev Neurosci. 2012;13(11):758­768. doi: 10.1038/nrn3357</mixed-citation><mixed-citation xml:lang="en">Menzel R. The honeybee as a model for understanding the basis of cognition. Nat Rev Neurosci. 2012;13(11):758­768. doi: 10.1038/nrn3357</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Niven J.E., Laughlin S.B. Energy limitation as a selective pressure on the evolution of sensory systems. J Exp Biol. 2008;211:1792­1804. doi: 10.1242/jeb.017574</mixed-citation><mixed-citation xml:lang="en">Niven J.E., Laughlin S.B. Energy limitation as a selective pressure on the evolution of sensory systems. J Exp Biol. 2008;211:1792­1804. doi: 10.1242/jeb.017574</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">O’shea K., Nash R. An introduction to convolutional neural networks. arXiv. 2015. doi: 10.48550/arXiv.1511.08458</mixed-citation><mixed-citation xml:lang="en">O’shea K., Nash R. An introduction to convolutional neural networks. arXiv. 2015. doi: 10.48550/arXiv.1511.08458</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Peng P., Wen Y., Yang Y., Yuan Q., Tang Z., Long H., Wang J. Multiagent bidirectionally­coordinated nets: Emergence of human­level coordination in learning to play StarCraft combat games. arXiv. 2017. doi: 10.48550/arXiv.1703.10069</mixed-citation><mixed-citation xml:lang="en">Peng P., Wen Y., Yang Y., Yuan Q., Tang Z., Long H., Wang J. Multiagent bidirectionally­coordinated nets: Emergence of human­level coordination in learning to play StarCraft combat games. arXiv. 2017. doi: 10.48550/arXiv.1703.10069</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Schulman J., Wolski F., Dhariwal P., Radford A., Klimov O. Proximal policy optimization algorithms. arXiv. 2017. doi: 10.48550/arXiv.1707.06347</mixed-citation><mixed-citation xml:lang="en">Schulman J., Wolski F., Dhariwal P., Radford A., Klimov O. Proximal policy optimization algorithms. arXiv. 2017. doi: 10.48550/arXiv.1707.06347</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Song K.-Y., Behzadfar M., Zhang W.-J. A dynamic pole motion approach for control of nonlinear hybrid soft legs: A preliminary study. Machines. 2022;10(10):875. doi: 10.3390/machines10100875</mixed-citation><mixed-citation xml:lang="en">Song K.-Y., Behzadfar M., Zhang W.-J. A dynamic pole motion approach for control of nonlinear hybrid soft legs: A preliminary study. Machines. 2022;10(10):875. doi: 10.3390/machines10100875</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Stanley K.O., Clune J., Lehman J., Miikkulainen R. Designing neural networks through neuroevolution. Nat Mach Intell. 2019;1(1): 24­35. doi: 10.1038/s42256­018­0006­z</mixed-citation><mixed-citation xml:lang="en">Stanley K.O., Clune J., Lehman J., Miikkulainen R. Designing neural networks through neuroevolution. Nat Mach Intell. 2019;1(1): 24­35. doi: 10.1038/s42256­018­0006­z</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Tschantz A., Anil K.S., Christopher L.B. Learning action-oriented models through active inference. PLoS Comput Biol. 2020;16(4): e1007805. doi: 10.1371/journal.pcbi.1007805</mixed-citation><mixed-citation xml:lang="en">Tschantz A., Anil K.S., Christopher L.B. Learning action-oriented models through active inference. PLoS Comput Biol. 2020;16(4): e1007805. doi: 10.1371/journal.pcbi.1007805</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Vezhnevets A.S., Osindero S., Schaul T., Heess N., Jaderberg M., Silver D., Kavukcuoglu K. FeUdal networks for hierarchical reinforcement learning. In: Proceedings of the 34&lt;sup&gt;th&lt;/sup&gt; International Conference on Machine Learning. Vol. 70 (ICML’17). JMLR.org, 2017;3540-3549</mixed-citation><mixed-citation xml:lang="en">Vezhnevets A.S., Osindero S., Schaul T., Heess N., Jaderberg M., Silver D., Kavukcuoglu K. FeUdal networks for hierarchical reinforcement learning. In: Proceedings of the 34&lt;sup&gt;th&lt;/sup&gt; International Conference on Machine Learning. Vol. 70 (ICML’17). JMLR.org, 2017;3540-3549</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Zador A.M. A critique of pure learning and what artificial neural networks can learn from animal brains. Nat Commun. 2019;10(1):3770. doi: 10.1038/s41467­019­11786­6</mixed-citation><mixed-citation xml:lang="en">Zador A.M. A critique of pure learning and what artificial neural networks can learn from animal brains. Nat Commun. 2019;10(1):3770. doi: 10.1038/s41467­019­11786­6</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>
