{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T11:20:04Z","timestamp":1769858404367,"version":"3.49.0"},"reference-count":44,"publisher":"Tech Science Press","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["CMC"],"published-print":{"date-parts":[[2025]]},"DOI":"10.32604\/cmc.2025.067117","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T07:24:21Z","timestamp":1753169061000},"page":"1339-1363","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Decoupling-Driven Cooperative Pursuit for Multi-UAV Systems: A Multi-Agent Reinforcement Learning Policy Optimization Approach"],"prefix":"10.32604","volume":"85","author":[{"given":"Lei","family":"Lei","sequence":"first","affiliation":[]},{"given":"Chengfu","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Huaimin","family":"Chen","sequence":"additional","affiliation":[]}],"member":"17807","published-online":{"date-parts":[[2025]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"7056","DOI":"10.1109\/TII.2024.3363084","article-title":"Moving target tracking by unmanned aerial vehicle: a survey and taxonomy","volume":"20","author":"Sun","year":"2024","journal-title":"IEEE Trans Ind Inform"},{"key":"ref2","series-title":"2019 International Conference on Unmanned Aircraft Systems (ICUAS)","first-page":"636","article-title":"Multi-UAV based autonomous wilderness search and rescue using target Iso-probability curves","author":"Kashino","year":"2019 Jun 11\u201314"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"4906","DOI":"10.1109\/JIOT.2020.3030240","article-title":"Cooperative path planning of UAVs & UGVs for a persistent surveillance task in urban environments","volume":"8","author":"Wu","year":"2020","journal-title":"IEEE Internet Things J"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1109\/TII.2019.2913683","article-title":"An algorithm of reactive collision free 3-D deployment of networked unmanned aerial vehicles for surveillance and monitoring","volume":"16","author":"Huang","year":"2020","journal-title":"IEEE Trans Ind Inform"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"2638","DOI":"10.1109\/TII.2018.2875041","article-title":"A method for optimized deployment of unmanned aerial vehicles for maximum coverage and minimum interference in cellular networks","volume":"15","author":"Huang","year":"2018","journal-title":"IEEE Trans Ind Inform"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/MCOM.2017.1700320","article-title":"UAV-aided cooperation for FSO communication systems","volume":"56","author":"Fawaz","year":"2018","journal-title":"IEEE Commun Mag"},{"key":"ref7","series-title":"2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)","first-page":"1342","article-title":"An introduction to multi-agent reinforcement learning and review of its application to autonomous mobility","author":"Schmidt","year":"2022 Oct 8\u201312"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neucom.2021.12.025","article-title":"Min-max Q-learning for multi-player pursuit-evasion games","volume":"475","author":"Selvakumar","year":"2022","journal-title":"Neurocomputing"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.1109\/TASE.2020.2980423","article-title":"Real-time acceleration-continuous path-constrained trajectory planning with built-In tradeoff between cruise and time-optimal motions","volume":"17","author":"Shen","year":"2020","journal-title":"IEEE Trans Autom Sci Eng"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1109\/TCYB.2019.2958548","article-title":"Cooperative pursuit with multi-pursuer and one faster free-moving evader","volume":"52","author":"Fang","year":"2022","journal-title":"IEEE Trans Cybern"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1090\/gsm\/213","author":"Tran","year":"2021","journal-title":"Hamilton-Jacobi equations: theory and applications"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"4432","DOI":"10.1109\/TNNLS.2020.3017762","article-title":"Synchronous fault-tolerant near-optimal control for discrete-time nonlinear PE game","volume":"32","author":"Yuan","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"4939","DOI":"10.1109\/TAC.2022.3168430","article-title":"Multiplayer pursuit-evasion differential games with malicious pursuers","volume":"67","author":"Xu","year":"2022","journal-title":"IEEE Trans Autom Control"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"1958","DOI":"10.1109\/TSMC.2022.3210022","article-title":"A region-based relay pursuit scheme for a pursuit-evasion game with a single evader and multiple pursuers","volume":"53","author":"Pan","year":"2022","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1007\/s40815-021-01158-y","article-title":"Visual range maneuver decision of unmanned combat aerial vehicle based on fuzzy reasoning","volume":"24","author":"Wu","year":"2022","journal-title":"Int J Fuzzy Syst"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1016\/j.automatica.2016.04.012","article-title":"Multi-player pursuit-evasion games with one superior evader","volume":"71","author":"Chen","year":"2016","journal-title":"Automatica"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1126\/science.aau6249","article-title":"Human-level performance in 3D multiplayer games with population-based reinforcement learning","volume":"364","author":"Jaderberg","year":"2019","journal-title":"Science"},{"key":"ref18","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/978-3-030-60990-0_12","author":"Zhang","year":"2021","journal-title":"Handbook of reinforcement learning and control"},{"key":"ref19","series-title":"NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"Lowe","year":"2017 Dec 4\u20139"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","article-title":"A survey and critique of multiagent deep reinforcement learning","volume":"33","author":"Hernandez-Leal","year":"2019","journal-title":"Auton Agents Multi Agent Syst"},{"key":"ref21","series-title":"Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems (AAMAS)","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"Sunehag","year":"2018 Jul 10\u201315"},{"key":"ref22","series-title":"Proceedings of the 35th International Conference on Machine Learning (ICML)","first-page":"4295","article-title":"Qmix: monotonic value function factorisation for deep multi-agent reinforcement learning","author":"Rashid","year":"2018 Jul 10\u201315"},{"key":"ref23","series-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","first-page":"5887","article-title":"Qtran: learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"Son","year":"2019 Jun 9\u201315"},{"key":"ref24","series-title":"Proceedings of the 32nd Association for the Advancement of Artificial Intelligence Conference on Artificial General Intelligence (AAAI)","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"Foerster","year":"2018 Feb 2\u20137"},{"key":"ref25","series-title":"Proceedings of the 33rd International Conference Neural Information Process System (NeurIPS)","first-page":"4403","article-title":"Liir: learning individual intrinsic reward in multi-agent reinforcement learning","author":"Du"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/4186303","article-title":"A UAV pursuit-evasion strategy based on DDPG and imitation learning","volume":"2022","author":"Fu","year":"2022","journal-title":"Int J Aerosp Eng"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"6859","DOI":"10.3390\/s24216859","article-title":"Multi-UAV escape target search: a multi-agent reinforcement learning method","volume":"24","author":"Liao","year":"2024","journal-title":"Sensors"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"7900","DOI":"10.1109\/TNNLS.2022.3146976","article-title":"Game of drones: multi-UAV pursuit-evasion game with online motion planning by deep reinforcement learning","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref29","series-title":"Proceedings of the 36th International Conference on Machine Learning (ICML)","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"Iqbal","year":"2019 Jun 9\u201315"},{"key":"ref30","series-title":"Proceedings of the 34th Association for the Advancement of Artificial Intelligence Conference Artificial Intelligence (AAAI)","first-page":"7211","article-title":"Multi-agent game abstraction via graph attention neural network","author":"Liu","year":"2020 Feb 7\u201312"},{"key":"ref31","series-title":"Proceedings of the 34th Association for the Advancement of Artificial Intelligence Conference Artificial Intelligence (AAAI)","first-page":"7236","article-title":"Multi-agent actor-critic with hierarchical graph attention network","author":"Ryu","year":"2020 Feb 7\u201312"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1109\/JAS.2024.124965","article-title":"Multi-UAV cooperative pursuit strategy with limited visual field in urban airspace: a multi-agent reinforcement learning approach","volume":"12","author":"Peng","year":"2025","journal-title":"IEEE\/CAA J Autom Sin"},{"key":"ref33","series-title":"Proceedings of the 36th International Conference on Neural Information Processing Systems (NeurIPS)","first-page":"12619","article-title":"Distributional reward estimation for effective multi-agent deep reinforcement learning","author":"Hu","year":"2022 Nov 28\u2013Dec 9"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.cja.2021.09.008","article-title":"Improving multi-target cooperative tracking guidance for UAV swarms using multi-agent reinforcement learning","volume":"35","author":"Zhou","year":"2022","journal-title":"Chin J Aeronaut"},{"key":"ref35","series-title":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","first-page":"13737","article-title":"Multi-UAV cooperative short-range combat via attention-based reinforcement learning using individual reward shaping","author":"Zhang","year":"2022 Oct 23\u201327"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"100303","DOI":"10.1016\/j.jnlest.2025.100303","article-title":"Multi-UAV path planning for multiple emergency payloads delivery in natural disaster scenarios","volume":"23","author":"Kutpanova","year":"2025","journal-title":"J Electron Sci Technol"},{"key":"ref37","series-title":"Proceedings of the 5th International Conference on Learning Representations (ICLR)","first-page":"1","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017 Apr 24\u201326"},{"key":"ref38","series-title":"Proceedings of the 4th International Conference on Learning Representations (ICLR)","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2016 May 2\u20134"},{"key":"ref39","series-title":"Proceedings of the 31st International Conference Neural Information Processing System (NeurIPS)","first-page":"6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017 Dec 4\u20139"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.neucom.2021.10.093","article-title":"Multi actor hierarchical attention critic with RNN-based feature extraction","volume":"471","author":"Shi","year":"2022","journal-title":"Neurocomputing"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1109\/TVT.2021.3129504","article-title":"Multi-agent reinforcement learning aided intelligent UAV swarm for target tracking","volume":"71","author":"Xia","year":"2021","journal-title":"IEEE Trans Veh Technol"},{"key":"ref42","series-title":"Proceedings of the 3rd International Conference on Learning Representations (ICLR)","first-page":"1","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015 May 7\u20139"},{"key":"ref43","series-title":"Proceedings of the Annual Conference of the IEEE Industrial Electronics Society","first-page":"846","article-title":"A high fidelity simulator for a auadrotor UAV using ROS and Gazebo","author":"Zhang","year":"2015 Nov 9\u201312"},{"key":"ref44","series-title":"Proceedings of the 36th Conference Conference on Neural Information Processing Systems (NeurIPS)","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","author":"Yu","year":"2022 Nov 28\u2013Dec 9"}],"container-title":["Computers, Materials & Continua"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cdn.techscience.cn\/files\/cmc\/2025\/TSP_CMC-85-1\/TSP_CMC_67117\/TSP_CMC_67117.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:01:17Z","timestamp":1763344877000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.techscience.com\/cmc\/v85n1\/63557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025]]},"published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.32604\/cmc.2025.067117","relation":{},"ISSN":["1546-2226"],"issn-type":[{"value":"1546-2226","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}