<?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">sapi</journal-id><journal-title-group><journal-title xml:lang="ru">Системный анализ и прикладная информатика</journal-title><trans-title-group xml:lang="en"><trans-title>«System analysis and applied information science»</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2309-4923</issn><issn pub-type="epub">2414-0481</issn><publisher><publisher-name>Belarusian National Technical University</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.21122/2309-4923-2025-4-41-48</article-id><article-id custom-type="elpub" pub-id-type="custom">sapi-774</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>Управление техническими объектами</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>Management of technical objects</subject></subj-group></article-categories><title-group><article-title>Усложнение акторов в TD3 и обучение по куррикулумому со структурной композицией на примере задачи отражения атак беспилотных летательных аппаратов</article-title><trans-title-group xml:lang="en"><trans-title>Actor complexification in TD3 and curriculum learning with structural composition for drone countering</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>Рулько</surname><given-names>Е. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Rulko</surname><given-names>E. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Рулько Евгений Викторович – кандидат технических наук, доцент. г. Минск</p><p>E-mail: eugeni1533@gmail.com</p><p> </p></bio><bio xml:lang="en"><p>Eugene V. Rulko – PhD of Engineering Sciences. Associate Professor,Minsk</p><p>E-mail: eugeni1533@gmail.com</p></bio><email xlink:type="simple">eugeni1533@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Военная академия Республики Беларусь</institution><country>Беларусь</country></aff><aff xml:lang="en"><institution>Military Academy of the Republic of Belarus</institution><country>Belarus</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>16</day><month>12</month><year>2025</year></pub-date><volume>0</volume><issue>4</issue><fpage>41</fpage><lpage>48</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Рулько Е.В., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Рулько Е.В.</copyright-holder><copyright-holder xml:lang="en">Rulko E.V.</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://sapi.bntu.by/jour/article/view/774">https://sapi.bntu.by/jour/article/view/774</self-uri><abstract><p>В работе предложены усложняющиеся акторы в рамках алгоритма двойного отсроченного глубокого детерминированного градиента политики (TD3), что предполагает использование различных векторов состояний для акторов и критиков с целью обеспечения сходимости алгоритма. Работа также описывает процесс агрегирования моделей, раздельно натренированных на датасетах или в симуляции на задачах с увеличивающейся сложностью, соединяя их вместе шаг за шагом в единую систему. Это позволяет использовать существующие алгоритмы, такие как YOLO, в системах обучения с подкреплением, осуществляя процесс объединения данных датчиков и постепенно увеличивая функциональность без потери сходимости. Предоставление ассистирования позволяет тренировать в симуляции системы машинного обучения на основе жестко запрограммированных алгоритмов, использующих упрощенные вектора состояний. Данные техники продемонстрированы на задаче построения системы защиты бронемашин от БПЛА.</p></abstract><trans-abstract xml:lang="en"><p>The work suggests complexifying actors within the framework of TD3 which involves the usage of different state vectors for actors and critics in order to assure convergence of the algorithm. It also describes a process of aggregating models, separately trained on datasets or in simulation on tasks with increasing difficulty, stitching everything together step by step into a single end-to-end system. It allows utilizing existing algorithms, such as YOLO, in reinforcement learning systems, performing sensor fusion and gradually adding functionality without losing convergence. Assistance providing allows training systems in simulation from hardcoded algorithms that use simplified states. These techniques are demonstrated on a particular task of building an anti-drone system for armored vehicles.</p></trans-abstract><kwd-group xml:lang="ru"><kwd>глубокое обучение с подкреплением</kwd><kwd>TD3</kwd><kwd>обучение по куррикулумому</kwd><kwd>объединение данных датчиков</kwd><kwd>БПЛА</kwd></kwd-group><kwd-group xml:lang="en"><kwd>deep reinforcement learning</kwd><kwd>TD3</kwd><kwd>curriculum learning</kwd><kwd>sensor fusion</kwd><kwd>UAV</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">NVIDIA Omniverse. Available at: https://www.nvidia.com/en-us/omniverse (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">NVIDIA Omniverse. Available at: https://www.nvidia.com/en-us/omniverse (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">NVIDIA Isaac Sim. Available at: https://developer.nvidia.com/isaac/sim (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">NVIDIA Isaac Sim. Available at: https://developer.nvidia.com/isaac/sim (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Narrowing the Sim2Real Gap with NVIDIA Isaac Sim. Nvidia. Available at: https://www.youtube.com/watch?v=VW-dOMBFj7o (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Narrowing the Sim2Real Gap with NVIDIA Isaac Sim. Nvidia. Available at: https://www.youtube.com/watch?v=VW-dOMBFj7o (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Unity. Available at: https://unity.com (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Unity. Available at: https://unity.com (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Unreal engine. Available at: https://www.unrealengine.com/en-US (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Unreal engine. Available at: https://www.unrealengine.com/en-US (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Loitering Munition Lancet Drone 3D Model. Renderhub. Available at: https://www.renderhub.com/sergeydzyuba/loitering-munition-lancet-drone (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Loitering Munition Lancet Drone 3D Model. Renderhub. Available at: https://www.renderhub.com/sergeydzyuba/loitering-munition-lancet-drone (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Unity ML-Agents Toolkit. GitHub. Available at: https://github.com/Unity-Technologies/ml-agents (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Unity ML-Agents Toolkit. GitHub. Available at: https://github.com/Unity-Technologies/ml-agents (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Grid Sensors for Unity ML-Agents. GitHub. Available at: https://github.com/mbaske/grid-sensor (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Grid Sensors for Unity ML-Agents. GitHub. Available at: https://github.com/mbaske/grid-sensor (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Haarnoja T., Zhou A., Abbeel P., Levine S. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. 2018. arXiv: 1801.01290. https://doi.org/10.48550/arXiv.1801.01290</mixed-citation><mixed-citation xml:lang="en">Haarnoja T., Zhou A., Abbeel P., Levine S. Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. 2018. arXiv: 1801.01290. https://doi.org/10.48550/arXiv.1801.01290</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Schulman J., Wolski F., Dhariwal P., Radford A., Klimov O. Proximal Policy Optimization Algorithms. 2017. arXiv: 1707.06347. https://doi.org/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. 2017. arXiv: 1707.06347. https://doi.org/10.48550/arXiv.1707.06347</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Lillicrap T.P., Hunt J.J, Pritzel A., Heess N., Erez T., Tassa Y., et al. Continuous control with deep reinforcement learning. 2019. arXiv: 1509.02971. https://doi.org/10.48550/arXiv.1509.02971</mixed-citation><mixed-citation xml:lang="en">Lillicrap T.P., Hunt J.J, Pritzel A., Heess N., Erez T., Tassa Y., et al. Continuous control with deep reinforcement learning. 2019. arXiv: 1509.02971. https://doi.org/10.48550/arXiv.1509.02971</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Fujimoto S., Herke van Hoof, Meger D. Addressing Function Approximation Error in Actor-Critic Methods. 2018. arXiv: 1802.09477. https://doi.org/10.48550/arXiv.1802.09477</mixed-citation><mixed-citation xml:lang="en">Fujimoto S., Herke van Hoof, Meger D. Addressing Function Approximation Error in Actor-Critic Methods. 2018. arXiv: 1802.09477. https://doi.org/10.48550/arXiv.1802.09477</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Rulko E.V. Complexification through gradual involvement and reward providing in deep reinforcement learning. System analysis and applied information science. 2024;4:13-20. https://doi.org/10.21122/2309-4923-2024-4-13-20</mixed-citation><mixed-citation xml:lang="en">Rulko E.V. Complexification through gradual involvement and reward providing in deep reinforcement learning. System analysis and applied information science. 2024;4:13-20. https://doi.org/10.21122/2309-4923-2024-4-13-20</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">ESC-50: Dataset for Environmental Sound Classification. GitHub. Available at: https://github.com/karolpiczak/ESC-50/tree/master (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">ESC-50: Dataset for Environmental Sound Classification. GitHub. Available at: https://github.com/karolpiczak/ESC-50/tree/master (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">DroneAudioDataset. GitHub. Available at: https://github.com/saraalemadi/DroneAudioDataset (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">DroneAudioDataset. GitHub. Available at: https://github.com/saraalemadi/DroneAudioDataset (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Drone Audio Detection Samples. Hugging Face. Available at: https://huggingface.co/datasets/geronimobasso/drone-audio-detection-samples (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Drone Audio Detection Samples. Hugging Face. Available at: https://huggingface.co/datasets/geronimobasso/drone-audio-detection-samples (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Vit_b_16. PyTorch documentation. Available at: https://docs.pytorch.org/vision/main/models/generated/torchvision.models.vit_b_16.html (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Vit_b_16. PyTorch documentation. Available at: https://docs.pytorch.org/vision/main/models/generated/torchvision.models.vit_b_16.html (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Smart Bee Colony Monitor: Clips of Beehive Sounds. Kaggle. Available at: https://www.kaggle.com/datasets/annajyang/beehive-sounds (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Smart Bee Colony Monitor: Clips of Beehive Sounds. Kaggle. Available at: https://www.kaggle.com/datasets/annajyang/beehive-sounds (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Time series classification. Dataset: MosquitoSound. Time series classification website. Available at: https://www.timeseriesclassification.com/description.php?Dataset=MosquitoSound (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Time series classification. Dataset: MosquitoSound. Time series classification website. Available at: https://www.timeseriesclassification.com/description.php?Dataset=MosquitoSound (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Audio Dataset of Low-Flying Aircraft: AeroSonicDB. Kaggle. Available at: https://www.kaggle.com/datasets/ gray8ed/audio-dataset-of-low-flying-aircraft-aerosonicdb (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Audio Dataset of Low-Flying Aircraft: AeroSonicDB. Kaggle. Available at: https://www.kaggle.com/datasets/gray8ed/audio-dataset-of-low-flying-aircraft-aerosonicdb (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">YOLO Drone Detection Dataset. Kaggle. Available at: https://www.kaggle.com/datasets/muki2003/yolo-drone-detection-dataset (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">YOLO Drone Detection Dataset. Kaggle. Available at: https://www.kaggle.com/datasets/muki2003/yolo-drone-detection-dataset (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Caltech-UCSD Birds-200-2011. Kaggle. Available at: https://www.kaggle.com/datasets/veeralakrishna/200-bird-species-with-11788-images/data (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Caltech-UCSD Birds-200-2011. Kaggle. Available at: https://www.kaggle.com/datasets/veeralakrishna/200-bird-species-with-11788-images/data (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">Perception Package. Unity documentation. Available at: https://docs.unity3d.com/Packages/com.unity.perception@1.0/manual/index.html (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Perception Package. Unity documentation. Available at: https://docs.unity3d.com/Packages/com.unity.perception@1.0/manual/index.html (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław Dębiak, Christy Dennison, et al. Dota 2 with Large Scale Deep Reinforcement Learning. 2019. arXiv: 1912.06680. https://doi.org/10.48550/arXiv.1912.06680</mixed-citation><mixed-citation xml:lang="en">Christopher Berner, Greg Brockman, Brooke Chan, Vicki Cheung, Przemysław Dębiak, Christy Dennison, et al. Dota 2 with Large Scale Deep Reinforcement Learning. 2019. arXiv: 1912.06680. https://doi.org/10.48550/arXiv.1912.06680</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">Articulation Body component reference. Unity documentation. Available at: https://docs.unity3d.com/6000.1/Documentation/Manual/class-ArticulationBody.html (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Articulation Body component reference. Unity documentation. Available at: https://docs.unity3d.com/6000.1/Documentation/Manual/class-ArticulationBody.html (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">Lowe R., Wu Y., Tamar A., Harb J., Abbeel P., Mordatch I. Multi-Agent Actor-Critic for Mixed CooperativeCompetitive Environments. 2020. arXiv: 1706.02275. https://doi.org/10.48550/arXiv.1706.02275</mixed-citation><mixed-citation xml:lang="en">Lowe R., Wu Y., Tamar A., Harb J., Abbeel P., Mordatch I. Multi-Agent Actor-Critic for Mixed CooperativeCompetitive Environments. 2020. arXiv: 1706.02275. https://doi.org/10.48550/arXiv.1706.02275</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Projects motion of pixels to a voxel. GitHub. Available at: https://github.com/ConsistentlyInconsistentYT/Pixeltovoxelprojector (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Projects motion of pixels to a voxel. GitHub. Available at: https://github.com/ConsistentlyInconsistentYT/Pixeltovoxelprojector (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit28"><label>28</label><citation-alternatives><mixed-citation xml:lang="ru">Tracking faint objects with cheap cameras. Consistently inconsistent. Available at: https://www.youtube.com/watch?v=m-b51C82-UE&amp;t=98s (accessed: 08 August 2025).</mixed-citation><mixed-citation xml:lang="en">Tracking faint objects with cheap cameras. Consistently inconsistent. Available at: https://www.youtube.com/watch?v=m-b51C82-UE&amp;t=98s (accessed: 08 August 2025).</mixed-citation></citation-alternatives></ref><ref id="cit29"><label>29</label><citation-alternatives><mixed-citation xml:lang="ru">Friston K. The free-energy principle: a unified brain theory? Nature Reviews Neuroscience. 2010;11:127–138. https://doi.org/10.1038/nrn2787</mixed-citation><mixed-citation xml:lang="en">Friston K. The free-energy principle: a unified brain theory? Nature Reviews Neuroscience. 2010;11:127–138. https://doi.org/10.1038/nrn2787</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>
