{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T15:58:08Z","timestamp":1778947088086,"version":"3.51.4"},"reference-count":26,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In intelligent multi-agent systems, particularly in drone combat scenarios, the challenges posed by rapidly changing environments and incomplete information significantly hinder effective strategy optimization. Traditional multi-agent reinforcement learning (MARL) approaches often encounter difficulties in adapting to the dynamic nature of adversarial environments, especially when enemy strategies are subject to continuous evolution, complicating agents\u2019 ability to respond effectively. To address these challenges, this paper introduces a novel enhanced MARL framework, MADDPG-SASP, which integrates an improved self-attention mechanism with self-play within the MADDPG algorithm, thereby facilitating superior strategy optimization. The self-attention mechanism empowers agents to adaptively extract critical environmental features, thereby enhancing both the speed and accuracy of perception and decision-making processes. Concurrently, the adaptive self-battling mechanism iteratively refines agent strategies through continuous adversarial interactions, thereby bolstering the stability and flexibility of their responses. Empirical results indicate that after 600 rounds, the win rate of agents employing this framework saw a substantial increase, rising from 26.17% with the original MADDPG to a perfect 100%. Further validation through comparative experiments underscores the method\u2019s efficacy, demonstrating considerable advantages in strategy optimization and agent performance in complex, dynamic environments. Moreover, in the Predator\u2013Prey Scenario combat environment, when the enemy side employs a multi-agent strategy, the win rate for the drone agent side can reach 98.5% and 100%.<\/jats:p>","DOI":"10.3390\/info16121050","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T08:49:22Z","timestamp":1764665362000},"page":"1050","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Optimization of Multi-Intelligent Body Strategies for UAV Adversarial Tasks Based on MADDPG-SASP"],"prefix":"10.3390","volume":"16","author":[{"given":"Zhenfei","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuyong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Xinjiang College of Science and Technology, Korla 841000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronic and Electrical Engineering, Wuhan Textile University, Wuhan 430200, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Xu, J., and Liang, G. (2025). Enhanced Q learning and deep reinforcement learning for unmanned combat intelligence planning in adversarial environments. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-13752-3"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Tedeschi, G., Papini, M., Metelli, A.M., and Restelli, M. (2025). Search or split: Policy gradient with adaptive policy space. Mach. Learn., 114.","DOI":"10.1007\/s10994-025-06820-2"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zhao, Z., and Wang, Y. (2025). Soft actor-critic algorithm and improved GNN model in secure access control of disaggregated optical networks. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-15225-z"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","article-title":"Deep Reinforcement Learning: A Brief Survey","volume":"34","author":"Arulkumaran","year":"2017","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1007\/s11277-025-11792-6","article-title":"A New DDPG-Based Algorithm for Sum Throughput Maximization in UAV-Assisted IRS-Empowered Wireless Sensor Network","volume":"141","author":"Amerimehr","year":"2025","journal-title":"Wirel. Pers. Commun."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.jmsy.2024.03.004","article-title":"From Nash Q-learning to nash-MADDPG: Advancements in multiagent control for multiproduct flexible manufacturing systems","volume":"74","author":"Waseem","year":"2024","journal-title":"J. Manuf. Syst."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhou, T., Liu, Z., Jin, W., and Han, Z. (2025). Intelligent maneuver decision-making for UAVs using the TD3-LSTM reinforcement learning algorithm under uncertain information. Front. Robot. AI, 12.","DOI":"10.3389\/frobt.2025.1645927"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"11265","DOI":"10.1007\/s11581-025-06567-9","article-title":"Research on DP-MPC control strategy based on active equalization system of bidirectional flyback transformer","volume":"31","author":"Kan","year":"2025","journal-title":"Ionics"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bartolomei, L., Teixeira, L., and Chli, M. (October, January 27). Semantic-Aware Active Perception for UAVs Using Deep Reinforcement Learning. Proceedings of the 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic.","DOI":"10.1109\/IROS51168.2021.9635893"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2424","DOI":"10.1109\/TWC.2022.3211533","article-title":"Joint Maneuver and Beamforming Design for UAV-Enabled Integrated Sensing and Communication","volume":"22","author":"Lyu","year":"2023","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_11","first-page":"1812","article-title":"Flight verification of multiple UAVs collaborative air combat imitating the intelligent behavior in hawks","volume":"35","author":"Duan","year":"2018","journal-title":"Control Theory Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"227629","DOI":"10.1109\/ACCESS.2020.3045934","article-title":"Mission-Oriented 3D Path Planning for High-Altitude Long-Endurance Solar-Powered UAVs With Optimal Energy Management","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Shen, Q., Zhang, D., He, Q., Ban, Y., and Zuo, F. (2024). A novel multi-objective dung beetle optimizer for Multi-UAV cooperative path planning. Heliyon, 10.","DOI":"10.1016\/j.heliyon.2024.e37286"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Chen, Y., Dong, Q., Shang, X., Wu, Z., and Wang, J. (2023). Multi-UAV Autonomous Path Planning in Reconnaissance Missions Considering Incomplete Information: A Reinforcement Learning Method. Drones, 7.","DOI":"10.3390\/drones7010010"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Sun, Y., Xia, H., Su, C., Zhang, R., Wang, J., and Jia, K. (2025). A multi-agent enhanced DDPG method for federated learning resource allocation in IoT. Comput. Commun., 233.","DOI":"10.1016\/j.comcom.2025.108066"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, C., Fu, Q., Chen, J., Lu, Y., Wang, Y., and Wu, H. (2025). FS-DDPG: Optimal Control of a Fan Coil Unit System Based on Safe Reinforcement Learning. Buildings, 15.","DOI":"10.3390\/buildings15020226"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lu, Y., Xu, C., and Wang, Y. (2024). Joint Computation Offloading and Trajectory Optimization for Edge Computing UAV: A KNN-DDPG Algorithm. Drones, 8.","DOI":"10.3390\/drones8100564"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2106","DOI":"10.1109\/TAC.2011.2179869","article-title":"Nonlinear Feedback Design for Fixed-Time Stabilization of Linear Control Systems","volume":"57","author":"Polyakov","year":"2012","journal-title":"IEEE Trans. Autom. Control"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Labbadi, M., Boubaker, S., Djemai, M., Mekni, S., and Bekrar, A. (2022). Fixed-Time Fractional-Order Global Sliding Mode Control for Nonholonomic Mobile Robot Systems under External Disturbances. Fractal Fract., 6.","DOI":"10.3390\/fractalfract6040177"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3747","DOI":"10.1109\/TWC.2017.2688328","article-title":"Energy-Efficient UAV Communication With Trajectory Optimization","volume":"16","author":"Zeng","year":"2017","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Feng, Z., Wu, Z., Zou, J., Cheng, L., Zhao, X., Zhang, X., Lu, J., Wang, C., Wang, Y., and Wang, H. (2025). Memristive Bellman solver for decision-making. Nat. Commun., 16.","DOI":"10.1038\/s41467-025-60085-w"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gadiraju, D.S., Karmakar, P., Shah, V.K., and Aggarwal, V. (2024). GLIDE: Multi-Agent Deep Reinforcement Learning for Coordinated UAV Control in Dynamic Military Environments. Information, 15.","DOI":"10.3390\/info15080477"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, Q., Yan, H., Chen, K., Wang, M., and Li, Z. (2025). Distributed Nash equilibrium solution for multi-agent game in adversarial environment: A reinforcement learning method. Automatica, 178.","DOI":"10.1016\/j.automatica.2025.112342"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.aej.2024.11.064","article-title":"Intelligent detection method of small targets in UAV based on attention mechanism and edge enhancement filtering","volume":"115","author":"Wu","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chansuparp, M., and Jitkajornwanich, K. (2022). A Novel Augmentative Backward Reward Function with Deep Reinforcement Learning for Autonomous UAV Navigation. Appl. Artif. Intell., 36.","DOI":"10.1080\/08839514.2022.2084473"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"454","DOI":"10.1016\/j.ins.2021.11.054","article-title":"Self-Attention-Based Multi-Agent Continuous Control Method in Cooperative Environments","volume":"585","author":"Liu","year":"2022","journal-title":"Inf. Sci."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/12\/1050\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T05:14:16Z","timestamp":1764911656000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/12\/1050"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":26,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["info16121050"],"URL":"https:\/\/doi.org\/10.3390\/info16121050","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}