{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:14:51Z","timestamp":1771949691112,"version":"3.50.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/tetci.2024.3451338","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T14:55:23Z","timestamp":1726584923000},"page":"1843-1859","source":"Crossref","is-referenced-by-count":7,"title":["Multi-Ship Dynamic Weapon-Target Assignment via Cooperative Distributional Reinforcement Learning With Dynamic Reward"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2904-7060","authenticated-orcid":false,"given":"Zhe","family":"Peng","sequence":"first","affiliation":[{"name":"School of Traffic and Transportation Engineering, Central South University, Changsha, China"}]},{"given":"Zhifeng","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Institute of Mechanical and Electrical Engineering, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1344-8880","authenticated-orcid":false,"given":"Xiao","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Traffic and Transportation Engineering, Central South University, Changsha, China"}]},{"given":"Feng","family":"Ye","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Complex Systems Simulation, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6365-275X","authenticated-orcid":false,"given":"Kuihua","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Systems Engineering, National University of Defense Technology, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1552-9620","authenticated-orcid":false,"given":"Guohua","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Automation, Central South University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1226-2801","authenticated-orcid":false,"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1287\/opre.6.3.346"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2003.808174"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2010.2049261"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2012.2231673"},{"key":"ref5","article-title":"Ship self air defense analysis for different operation conditions via simulation","author":"Kmek","year":"2007"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S1004-4132(06)60097-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.vehcom.2022.100469"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2018.10.015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(92)90077-M"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-022-04525-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2020.100719"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.14429\/dsj.51.2239"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WCICA.2006.1713032"},{"key":"ref14","article-title":"Reinforcement learning framework for combinatorial optimization problem application to dynamic weapon target assignment","author":"Yoon","year":"2024"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3139802"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3934\/era.2024069"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3339540"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/522"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11590-014-0823-x"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2018.08.015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21236\/ADA953517"},{"key":"ref22","article-title":"Dynamic weapon-target assignment problems with vulnerable C2 nodes","author":"Hosein","year":"1988"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3182\/20140824-6-za-1003.02150"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2006.09.011"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2019.01.015"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2784187"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2018.06.014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1651\/1\/012062"},{"key":"ref29","article-title":"Solving weapon target assignment problem with dynamic programming","volume":"32","author":"Sikanen","year":"2008","journal-title":"Independent Res. Projects Appl. Math."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3096997"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105612"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/CCC58697.2023.10240428"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.dt.2022.04.001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/cth2.12413"},{"issue":"2","key":"ref35","first-page":"757","article-title":"Research on dynamically corrective hit probability model of anti-air missile integrated in war game system","volume":"30","author":"Huang","year":"2022","journal-title":"Eng. Lett."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1030.0086"},{"issue":"6","key":"ref37","doi-asserted-by":"crossref","first-page":"47","DOI":"10.24018\/ejece.2022.6.6.478","article-title":"Research on combat composition of ship-to-air missile formation","volume":"6","author":"Dou","year":"2022","journal-title":"Eur. J. Elect. Eng. Comput. Sci."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3209655"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3188904"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3127925"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3293193"},{"key":"ref42","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"},{"issue":"1","key":"ref43","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","first-page":"23049","article-title":"RMIX: Learning risk-sensitive policies for cooperative reinforcement learning agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Qiu","year":"2021"},{"key":"ref45","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare","year":"2017"},{"key":"ref46","first-page":"29","article-title":"An analysis of categorical distributional reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Rowland","year":"2018"},{"issue":"10","key":"ref47","first-page":"9144","article-title":"Distributional reinforcement learning via moment matching","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"35","author":"Nguyen-Tang","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29681"},{"key":"ref49","first-page":"20208","article-title":"Interpretable reward redistribution in reinforcement learning: A causal approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang","year":"2024"},{"key":"ref50","first-page":"10376","article-title":"Keeping your distance: Solving sparse reward tasks using self-balancing shaped rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Trott","year":"2019"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref52","article-title":"QPLEX: Duplex dueling multi-agent q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref53","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Rashid","year":"2020"},{"key":"ref54","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref55","first-page":"1","article-title":"A unified framework for factorizing distributional value functions for multi-agent reinforcement learning","volume":"24","author":"Sun","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533636"},{"issue":"2","key":"ref57","first-page":"33","article-title":"Ballistic missile defense: Concepts and history","volume":"114","author":"Flax","year":"1985","journal-title":"Daedalus"},{"key":"ref58","article-title":"Multi-ship cooperative air defense model based on queuing theory","author":"Ma","year":"2022"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSEE.2015.00035"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7433297\/10939044\/10681512.pdf?arnumber=10681512","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:30:38Z","timestamp":1764095438000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10681512\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2024.3451338","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}