{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:25:18Z","timestamp":1782887118626,"version":"3.54.5"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T00:00:00Z","timestamp":1715212800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T00:00:00Z","timestamp":1715212800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61790552"],"award-info":[{"award-number":["61790552"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Evolving Systems"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s12530-024-09587-4","type":"journal-article","created":{"date-parts":[[2024,5,9]],"date-time":"2024-05-09T09:02:56Z","timestamp":1715245376000},"page":"1681-1699","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Preference-based experience sharing scheme for multi-agent reinforcement learning in multi-target environments"],"prefix":"10.1007","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8586-9834","authenticated-orcid":false,"given":"Xuan","family":"Zuo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pu","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui-Yan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhun-Ga","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,5,9]]},"reference":[{"issue":"6","key":"9587_CR1","doi-asserted-by":"publisher","first-page":"1136","DOI":"10.1287\/opre.1070.0440","volume":"55","author":"RK Ahuja","year":"2007","unstructured":"Ahuja RK, Kumar A, Jha KC, Orlin JB (2007) Exact and heuristic algorithms for the weapon-target assignment problem. Oper Res 55(6):1136\u20131146. https:\/\/doi.org\/10.1287\/opre.1070.0440","journal-title":"Oper Res"},{"key":"9587_CR2","unstructured":"Albrecht SV, Christianos F, Sch\u00e4fer L (2023) Multi-agent reinforcement learning: foundations and modern approaches. MIT Press, Cambridge. https:\/\/www.marl-book.com"},{"issue":"6","key":"9587_CR3","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran K, Deisenroth MP, Brundage M, Bharath AA (2017) Deep reinforcement learning: a brief survey. IEEE Signal Process Mag 34(6):26\u201338. https:\/\/doi.org\/10.1109\/MSP.2017.2743240","journal-title":"IEEE Signal Process Mag"},{"key":"9587_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","volume":"13","author":"AG Barto","year":"1983","unstructured":"Barto AG, Sutton RS, Anderson CW (1983) Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans Syst Man Cybern 13:834\u2013846. https:\/\/doi.org\/10.1109\/TSMC.1983.6313077","journal-title":"IEEE Trans Syst Man Cybern"},{"key":"9587_CR5","doi-asserted-by":"publisher","unstructured":"Bellingham J, Richards A, How JP (2002) Receding horizon control of autonomous aerial vehicles. In: ACC2002 (ed) Proceedings of the 2002 American control conference, vol 5. American Automatic Control Council, Anchorage, pp 3741\u20133746. https:\/\/doi.org\/10.1109\/ACC.2002.1024509","DOI":"10.1109\/ACC.2002.1024509"},{"key":"9587_CR6","unstructured":"Bello I, Pham H, Le QV, Norouzi M, Bengio S (2016) Neural combinatorial optimization with reinforcement learning. ArXiv CoRR arXiv:abs\/1611.09940"},{"key":"9587_CR7","unstructured":"Christianos F, Sch\u00e4fer L, Albrecht SV (2020) Shared experience actor-critic for multi-agent reinforcement learning. In: Larochelle H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Proceedings of the 34th international conference on neural information processing systems. NIPS\u201920. WASET, Red Hook, pp 10707\u201310717"},{"key":"9587_CR8","unstructured":"Degris T, White M, Sutton RS (2012) Off-policy actor-critic. In: Langford J, Pineau J (eds) Proceedings of the 29th international conference on machine learning. IMLS, Edinburgh, pp 179\u2013186"},{"key":"9587_CR9","doi-asserted-by":"publisher","unstructured":"Foerster JN, Farquhar G, Afouras T, Nardelli N, Whiteson S (2018) Counterfactual multi-agent policy gradients. In: Furman J, Marchant G, Price H, Rossi F (eds) Proceedings of the thirty-second AAAI conference on artificial intelligence. AAAI\u201918\/IAAI\u201918\/EAAI\u201918. AAAI Press, New Orleans, pp 2974\u20132982. https:\/\/doi.org\/10.1609\/aaai.v32i1.11794","DOI":"10.1609\/aaai.v32i1.11794"},{"issue":"3\u20134","key":"9587_CR10","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1561\/2200000071","volume":"11","author":"V Fran\u00e7ois-Lavet","year":"2018","unstructured":"Fran\u00e7ois-Lavet V, Henderson P, Islam R, Bellemare MG, Pineau J (2018) An introduction to deep reinforcement learning. Found Trends Mach Learn 11(3\u20134):219\u2013354. https:\/\/doi.org\/10.1561\/2200000071","journal-title":"Found Trends Mach Learn"},{"issue":"2","key":"9587_CR11","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer S, Diepold K (2022) Multi-agent deep reinforcement learning: a survey. Artif Intell Rev 55(2):895\u2013943. https:\/\/doi.org\/10.1007\/s10462-021-09996-w","journal-title":"Artif Intell Rev"},{"issue":"6","key":"9587_CR12","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TSMCC.2012.2218595","volume":"42","author":"I Grondman","year":"2012","unstructured":"Grondman I, Busoniu L, Lopes GAD, Babuska R (2012) A survey of actor-critic reinforcement learning: standard and natural policy gradients. IEEE Trans Syst Man Cybern Part C (Appl Rev) 42(6):1291\u20131307. https:\/\/doi.org\/10.1109\/TSMCC.2012.2218595","journal-title":"IEEE Trans Syst Man Cybern Part C (Appl Rev)"},{"key":"9587_CR13","doi-asserted-by":"publisher","unstructured":"Gupta JK, Egorov M, Kochenderfer M (2017) Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar G, Rodriguez-Aguilar JA (eds) Autonomous agents and multiagent systems. IFAAMAS, Cham, pp 66\u201383. https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"9587_CR14","unstructured":"Haarnoja T, Tang H, Abbeel P, Levine S (2017) Reinforcement learning with deep energy-based policies. In: Precup D, Teh YW (eds) Proceedings of the 34th international conference on machine learning. ICML\u201917, vol 70. IMLS, pp 1352\u20131361"},{"issue":"6","key":"9587_CR15","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","volume":"33","author":"P Hernandez-Leal","year":"2019","unstructured":"Hernandez-Leal P, Kartal B, Taylor ME (2019) A survey and critique of multiagent deep reinforcement learning. Auton Agents Multi-Agent Syst 33(6):750\u2013797. https:\/\/doi.org\/10.1007\/s10458-019-09421-1","journal-title":"Auton Agents Multi-Agent Syst"},{"key":"9587_CR16","unstructured":"Hua W, Fan L, Li L, Mei K, Ji J, Ge Y, Hemphill L, Zhang Y (2023) War and peace (waragent): large language model-based multi-agent simulation of world wars. arXiv preprint arXiv:2311.17227"},{"issue":"6443","key":"9587_CR17","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1126\/science.aau6249","volume":"364","author":"M Jaderberg","year":"2019","unstructured":"Jaderberg M, Czarnecki WM, Dunning I, Marris L, Lever G, Casta\u00f1eda AG, Beattie C, Rabinowitz NC, Morcos AS, Ruderman A, Sonnerat N, Green T, Deason L, Leibo JZ, Silver D, Hassabis D, Kavukcuoglu K, Graepel T (2019) Human-level performance in 3d multiplayer games with population-based reinforcement learning. Science 364(6443):859\u2013865. https:\/\/doi.org\/10.1126\/science.aau6249","journal-title":"Science"},{"key":"9587_CR18","doi-asserted-by":"publisher","unstructured":"Kalakanti AK, Verma S, Paul T, Yoshida T (2019) Rl solver pro: reinforcement learning for solving vehicle routing problem. In: Casuarina M, Meru B (eds) 2019 1st international conference on artificial intelligence and data sciences. Sreyas Institute Of Engineering and Technology, Ipoh, pp 94\u201399. https:\/\/doi.org\/10.1109\/AiDAS47888.2019.8970890","DOI":"10.1109\/AiDAS47888.2019.8970890"},{"issue":"15","key":"9587_CR19","doi-asserted-by":"publisher","first-page":"10153","DOI":"10.1007\/s00500-021-05923-x","volume":"25","author":"O Karasakal","year":"2021","unstructured":"Karasakal O, Karasakal E, Silav A (2021) A multi-objective approach for dynamic missile allocation using artificial neural networks for time sensitive decisions. Soft Comput 25(15):10153\u201310166. https:\/\/doi.org\/10.1007\/s00500-021-05923-x","journal-title":"Soft Comput"},{"key":"9587_CR20","doi-asserted-by":"publisher","unstructured":"Kumar R, Hyland DC (2001) Control law design using repeated trials. In: ACC2001 (ed) Proceedings of the 2001 American control conference, vol 2. American Automatic Control Council, Arlington, pp 837\u2013842. https:\/\/doi.org\/10.1109\/ACC.2001.945820","DOI":"10.1109\/ACC.2001.945820"},{"issue":"1","key":"9587_CR21","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/S1568-4946(02)00027-3","volume":"2","author":"Z Lee","year":"2002","unstructured":"Lee Z, Lee C, Su S (2002) An immunity-based ant colony optimization algorithm for solving weapon-target assignment problem. Appl Soft Comput 2(1):39\u201347. https:\/\/doi.org\/10.1016\/S1568-4946(02)00027-3","journal-title":"Appl Soft Comput"},{"key":"9587_CR22","doi-asserted-by":"publisher","unstructured":"Lee D, Shin MK, Choi H (2020) Weapon target assignment problem with interference constraints. AIAA Scitech 2020 Forum. AIAA, Orlando. https:\/\/doi.org\/10.2514\/6.2020-0388","DOI":"10.2514\/6.2020-0388"},{"key":"9587_CR23","unstructured":"Li Y (2018) Deep reinforcement learning. ArXiv CoRR arXiv:abs\/1810.06339"},{"issue":"9","key":"9587_CR24","doi-asserted-by":"publisher","first-page":"486","DOI":"10.3390\/aerospace9090486","volume":"9","author":"W Li","year":"2022","unstructured":"Li W, Lyu Y, Dai S, Chen H, Shi J, Li Y (2022) A multi-target consensus-based auction algorithm for distributed target assignment in cooperative beyond-visual-range air combat. Aerospace 9(9):486. https:\/\/doi.org\/10.3390\/aerospace9090486","journal-title":"Aerospace"},{"key":"9587_CR25","doi-asserted-by":"publisher","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, Heess N, Erez T, Tassa Y, Silver D, Wierstra D (2016) Continuous control with deep reinforcement learning. In: Bengio Y, LeCun Y (eds) 4th International conference on learning representations, conference track proceedings. ICLR, San Juan. https:\/\/doi.org\/10.48550\/arXiv.1509.02971","DOI":"10.48550\/arXiv.1509.02971"},{"key":"9587_CR26","unstructured":"Lloyd SP, Witsenhause HS (1986) Weapon allocation is NP-complete. In: Crosbie R, Luker P (eds) Proceeding of the IEEE summer simulation conference. IEEE, Reno, pp 1054\u20131058"},{"key":"9587_CR27","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel P, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. In: Luxburg UV, Guyon I (eds) Proceedings of the 31st international conference on neural information processing systems. NIPS\u201917. WASET, Long Beach, pp 6382\u20136393"},{"key":"9587_CR28","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s12065-022-00703-4","volume":"17","author":"C Lu","year":"2022","unstructured":"Lu C, Bao Q, Xia S, Qu C (2022) Centralized reinforcement learning for multi-agent cooperative environments. Evol Intell 17:267\u2013273. https:\/\/doi.org\/10.1007\/s12065-022-00703-4","journal-title":"Evol Intell"},{"key":"9587_CR29","doi-asserted-by":"publisher","first-page":"67319","DOI":"10.1109\/ACCESS.2019.2918703","volume":"7","author":"L Lv","year":"2019","unstructured":"Lv L, Zhang S, Ding D, Wang Y (2019) Path planning via an improved DQN-based learning policy. IEEE Access 7:67319\u201367330. https:\/\/doi.org\/10.1109\/ACCESS.2019.2918703","journal-title":"IEEE Access"},{"key":"9587_CR30","doi-asserted-by":"publisher","unstructured":"Maddula T, Minai AA, Polycarpou MM (2004) Multi-target assignment and path planning for groups of UAVs, Chapter 1. In: Butenko S, Murphey R, Pardalos PM (eds) Recent developments in cooperative control and optimization, Boston, pp 261\u2013272. https:\/\/doi.org\/10.1007\/978-1-4613-0219-3_15","DOI":"10.1007\/978-1-4613-0219-3_15"},{"key":"9587_CR31","doi-asserted-by":"publisher","unstructured":"McLain TW, Chandler PR, Rasmussen S, Pachter M (2001) Cooperative control of UAV rendezvous. In: ACC2001 (ed) Proceedings of the 2001 American control conference, vol. 3. American Automatic Control Council, Arlington, pp 2309\u20132314. https:\/\/doi.org\/10.1109\/ACC.2001.946096","DOI":"10.1109\/ACC.2001.946096"},{"issue":"14","key":"9587_CR32","doi-asserted-by":"publisher","first-page":"16315","DOI":"10.1109\/JSEN.2021.3074826","volume":"21","author":"F Meng","year":"2021","unstructured":"Meng F, Tian K, Wu C (2021) Deep reinforcement learning-based radar network target assignment. IEEE Sens J 21(14):16315\u201316327. https:\/\/doi.org\/10.1109\/JSEN.2021.3074826","journal-title":"IEEE Sens J"},{"key":"9587_CR33","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G, Petersen S, Beattie C, Sadik A, Antonoglou I, King H, Kumaran D, Wierstra D, Legg S, Hassabis D (2015) Human-level control through deep reinforcement learning. Nature 518:529\u2013533. https:\/\/doi.org\/10.1038\/nature14236","journal-title":"Nature"},{"key":"9587_CR34","unstructured":"Mnih V, Badia AP, Mirza M, Graves A, Harley T, Lillicrap TP, Silver D, Kavukcuoglu K (2016) Asynchronous methods for deep reinforcement learning. In: Balcan MF, Weinberger KQ (eds) Proceedings of the 33rd international conference on machine learning. ICML\u201916, vol 48. IMLS, New York, pp 1928\u20131937"},{"issue":"1","key":"9587_CR35","doi-asserted-by":"publisher","first-page":"53","DOI":"10.2514\/1.I011150","volume":"20","author":"H Na","year":"2023","unstructured":"Na H, Ahn J, Moon I (2023) Weapon-target assignment by reinforcement learning with pointer network. J Aerosp Inf Syst 20(1):53\u201359. https:\/\/doi.org\/10.2514\/1.I011150","journal-title":"J Aerosp Inf Syst"},{"key":"9587_CR36","unstructured":"Nazari M, Oroojlooy A, Tak\u00e1\u010d M, Snyder LV (2018) Reinforcement learning for solving the vehicle routing problem. In: Bengio S, Wallach HM, Cesa-Bianchi N (eds) Proceedings of the 32nd international conference on neural information processing systems. NIPS\u201918. WASET, Montr\u00e9al, pp 9861\u20139871"},{"key":"9587_CR37","doi-asserted-by":"publisher","first-page":"103946","DOI":"10.1016\/j.artint.2023.103946","volume":"321","author":"K Okumura","year":"2023","unstructured":"Okumura K, D\u00e9fago X (2023) Solving simultaneous target assignment and path planning efficiently with time-independent execution. Artif Intell 321:103946. https:\/\/doi.org\/10.1016\/j.artint.2023.103946","journal-title":"Artif Intell"},{"key":"9587_CR38","unstructured":"Omidshafiei S, Pazis J, Amato C, How JP, Vian J (2017) Deep decentralized multi-task multi-agent reinforcement learning under partial observability. In: Precup D, Teh YW (eds) Proceedings of the 34th international conference on machine learning. ICML\u201917. IMLS, Sydney, pp 2681\u20132690"},{"key":"9587_CR39","doi-asserted-by":"crossref","unstructured":"Park JS, O\u2019Brien JC, Cai CJ, Morris MR, Liang P, Bernstein MS (2023) Generative agents: interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442","DOI":"10.1145\/3586183.3606763"},{"key":"9587_CR40","unstructured":"Rashid T, Samvelyan M, Schroeder C, Farquhar G, Foerster J, Whiteson S (2018) QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Dy JG, Krause A (eds) Proceedings of the 35th international conference on machine learning, vol 80. PMLR, Stockholmsm\u00e4ssan, Stockholm, pp 4295\u20134304. https:\/\/proceedings.mlr.press\/v80\/rashid18a.html"},{"key":"9587_CR41","doi-asserted-by":"publisher","unstructured":"Rasmussen S, Chandler P, Mitchell J, Schumacher C, Sparks A (2003) Optimal vs. heuristic assignment of cooperative autonomous unmanned air vehicles. AIAA Guidance, Navigation, and Control Conference and Exhibit. AIAA, Austin. https:\/\/doi.org\/10.2514\/6.2003-5586","DOI":"10.2514\/6.2003-5586"},{"key":"9587_CR42","doi-asserted-by":"publisher","unstructured":"Richards A, Bellingham J, Tillerson M, How J (2002) Coordination and control of multiple UAVs. AIAA guidance, navigation, and control conference and exhibit. AIAA, Monterey. https:\/\/doi.org\/10.2514\/6.2002-4588","DOI":"10.2514\/6.2002-4588"},{"key":"9587_CR43","unstructured":"Schulman J, Levine S, Moritz P, Jordan M, Abbeel P (2015) Trust region policy optimization. In: Bach F, Blei D (eds) Proceedings of the 32nd international conference on machine learning. ICML\u201915, vol. 37. IMLS, Lille, pp 1889\u20131897"},{"key":"9587_CR44","doi-asserted-by":"publisher","unstructured":"Shin MK, Lee D, Choi H (2019) Weapon-target assignment problem with interference constraints using mixed-integer linear programming. Asia Pacific International Symposium on Aerospace Technology. RAeS Australian Division and Engineers Australia, Gold Coast, pp 2382\u20132392. https:\/\/doi.org\/10.48550\/arXiv.1911.12567","DOI":"10.48550\/arXiv.1911.12567"},{"issue":"8","key":"9587_CR45","doi-asserted-by":"publisher","first-page":"3601","DOI":"10.1007\/s00500-022-06820-7","volume":"26","author":"M Shokoohi","year":"2022","unstructured":"Shokoohi M, Afsharchi M, Shah-Hoseini H (2022) Dynamic distributed constraint optimization using multi-agent reinforcement learning. Soft Comput 26(8):3601\u20133629. https:\/\/doi.org\/10.1007\/s00500-022-06820-7","journal-title":"Soft Comput"},{"key":"9587_CR46","unstructured":"Silver D, Lever G, Heess N, Degris T, Wierstra D, Riedmiller M (2014) Deterministic policy gradient algorithms. In: Xing EP, Jebara T (eds) Proceedings of the 31st international conference on machine learning, vol 32. IMLS, Beijing, pp 387\u2013395"},{"key":"9587_CR47","doi-asserted-by":"publisher","unstructured":"Singh L, Fuller J (2001) Trajectory generation for a UAV in urban terrain, using nonlinear MPC. In: ACC2001 (ed) Proceedings of the 2001 American control conference, vol 3. American Automatic Control Council, Arlington, pp 2301\u20132308. https:\/\/doi.org\/10.1109\/ACC.2001.946095","DOI":"10.1109\/ACC.2001.946095"},{"issue":"12","key":"9587_CR48","doi-asserted-by":"publisher","first-page":"7387","DOI":"10.1109\/TMC.2022.3208457","volume":"22","author":"F Song","year":"2023","unstructured":"Song F, Xing H, Wang X, Luo S, Dai P, Xiao Z, Zhao B (2023) Evolutionary multi-objective reinforcement learning based trajectory control and task offloading in UAV-assisted mobile edge computing. IEEE Trans Mob Comput 22(12):7387\u20137405. https:\/\/doi.org\/10.1109\/TMC.2022.3208457","journal-title":"IEEE Trans Mob Comput"},{"key":"9587_CR49","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K, Graepel T (2018) Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Andre E, Koenig S (eds) Proceedings of the 17th international conference on autonomous agents and multiagent systems. AAMAS \u201918. International Foundation for Autonomous Agents and Multiagent Systems, Richland, pp 2085\u20132087"},{"key":"9587_CR50","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction, 2nd edn. MIT Press, Cambridge. https:\/\/mitpress.mit.edu\/9780262352703\/reinforcement-learning\/"},{"key":"9587_CR51","unstructured":"Vinyals O, Fortunato M, Jaitly N (2015) Pointer networks. In: Cortes C, Lee DD, Sugiyama M, Garnett R (eds) Proceedings of the 28th international conference on neural information processing systems. NIPS\u201915, vol 2. WASET, Montr\u00e9al, pp 2692\u20132700"},{"key":"9587_CR52","doi-asserted-by":"publisher","unstructured":"Wang S, Chen W (2012) Solving weapon-target assignment problems by cultural particle swarm optimization. In: IHMSC\u201912 (ed) Proceedings of the 2012 4th international conference on intelligent human-machine systems and cybernetics, vol 1. IEEE Computer Society, Nanchang, pp 141\u2013144. https:\/\/doi.org\/10.1109\/IHMSC.2012.41","DOI":"10.1109\/IHMSC.2012.41"},{"issue":"2","key":"9587_CR53","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1016\/j.cja.2017.09.005","volume":"31","author":"Z Wang","year":"2018","unstructured":"Wang Z, Liu L, Long T, Wen Y (2018) Multi-UAV reconnaissance task allocation for heterogeneous targets using an opposition-based genetic algorithm with double-chromosome encoding. Chin J Aeronaut 31(2):339\u2013350. https:\/\/doi.org\/10.1016\/j.cja.2017.09.005","journal-title":"Chin J Aeronaut"},{"issue":"4","key":"9587_CR54","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/S0019-9958(77)90354-0","volume":"34","author":"IH Witten","year":"1977","unstructured":"Witten IH (1977) An adaptive optimal controller for discrete-time Markov environments. Inf Control 34(4):286\u2013295. https:\/\/doi.org\/10.1016\/S0019-9958(77)90354-0","journal-title":"Inf Control"},{"key":"9587_CR55","doi-asserted-by":"publisher","first-page":"75998","DOI":"10.1109\/ACCESS.2022.3190972","volume":"10","author":"Y Wu","year":"2022","unstructured":"Wu Y, Lei Y, Zhu Z, Yang X, Li Q (2022) Dynamic multitarget assignment based on deep reinforcement learning. IEEE Access 10:75998\u201376007. https:\/\/doi.org\/10.1109\/ACCESS.2022.3190972","journal-title":"IEEE Access"},{"issue":"1","key":"9587_CR56","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1109\/TETCI.2023.3304948","volume":"8","author":"Z Xiao","year":"2024","unstructured":"Xiao Z, Xing H, Zhao B, Qu R, Luo S, Dai P, Li K, Zhu Z (2024) Deep contrastive representation learning with self-distillation. IEEE Trans Emerg Top Comput Intell 8(1):3\u201315. https:\/\/doi.org\/10.1109\/TETCI.2023.3304948","journal-title":"IEEE Trans Emerg Top Comput Intell"},{"issue":"12","key":"9587_CR57","doi-asserted-by":"publisher","first-page":"2706","DOI":"10.1016\/j.cja.2019.05.012","volume":"32","author":"Z Zhen","year":"2019","unstructured":"Zhen Z, Zhu P, Xue Y, Ji Y (2019) Distributed intelligent self-organized mission planning of multi-UAV for dynamic targets cooperative search-attack. Chin J Aeronaut 32(12):2706\u20132716. https:\/\/doi.org\/10.1016\/j.cja.2019.05.012","journal-title":"Chin J Aeronaut"},{"key":"9587_CR58","doi-asserted-by":"publisher","unstructured":"Zhu B, Zou F, Wei J (2011) A novel approach to solving weapon-target assignment problem based on hybrid particle swarm optimization algorithm. In: EMEIT2011 (ed) Proceedings of the 2011 international conference on electronic and mechanical engineering and information technology, vol 3. IEEE, Harbin, pp 1385\u20131387. https:\/\/doi.org\/10.1109\/EMEIT.2011.6023352","DOI":"10.1109\/EMEIT.2011.6023352"},{"issue":"9","key":"9587_CR59","doi-asserted-by":"publisher","first-page":"2040","DOI":"10.3969\/j.issn.1000-1093.2021.09.025","volume":"42","author":"J Zhu","year":"2021","unstructured":"Zhu J, Zhao C, Li X, Bao W (2021) Multi-target assignment and intelligent decision based on reinforcement learning. Acta Armamentarii 42(9):2040\u20132048. https:\/\/doi.org\/10.3969\/j.issn.1000-1093.2021.09.025","journal-title":"Acta Armamentarii"},{"issue":"S1","key":"9587_CR60","doi-asserted-by":"publisher","first-page":"726910","DOI":"10.7527\/S1000-6893.2022.26910","volume":"43","author":"Z Zou","year":"2022","unstructured":"Zou Z, Chen Q (2022) Decision tree-based target assignment for confrontation of multiple space vehicles. Acta Aeronaut Astronaut Sin 43(S1):726910. https:\/\/doi.org\/10.7527\/S1000-6893.2022.26910","journal-title":"Acta Aeronaut Astronaut Sin"}],"container-title":["Evolving Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-024-09587-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12530-024-09587-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12530-024-09587-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,23]],"date-time":"2024-08-23T20:02:24Z","timestamp":1724443344000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12530-024-09587-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,9]]},"references-count":60,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["9587"],"URL":"https:\/\/doi.org\/10.1007\/s12530-024-09587-4","relation":{},"ISSN":["1868-6478","1868-6486"],"issn-type":[{"value":"1868-6478","type":"print"},{"value":"1868-6486","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,9]]},"assertion":[{"value":"28 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 April 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 May 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}