{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T02:47:17Z","timestamp":1769741237800,"version":"3.49.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"31","license":[{"start":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T00:00:00Z","timestamp":1722988800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T00:00:00Z","timestamp":1722988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Outstanding Youth Talents Support Program","award":["61822304"],"award-info":[{"award-number":["61822304"]}]},{"name":"Basic Science Center Programs of NSFC","award":["62088101"],"award-info":[{"award-number":["62088101"]}]},{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX0100"],"award-info":[{"award-number":["2021SHZDZX0100"]}]},{"name":"Shanghai Municipal of Science and Technology Project","award":["19511132101"],"award-info":[{"award-number":["19511132101"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1007\/s00521-024-10261-8","type":"journal-article","created":{"date-parts":[[2024,8,7]],"date-time":"2024-08-07T19:02:20Z","timestamp":1723057340000},"page":"19667-19690","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Mean policy-based proximal policy optimization for maneuvering decision in multi-UAV air combat"],"prefix":"10.1007","volume":"36","author":[{"given":"Yifan","family":"Zheng","sequence":"first","affiliation":[]},{"given":"Bin","family":"Xin","sequence":"additional","affiliation":[]},{"given":"Bin","family":"He","sequence":"additional","affiliation":[]},{"given":"Yulong","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,7]]},"reference":[{"key":"10261_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.23919\/CSMS.2021.0003","volume":"1","author":"B Xin","year":"2021","unstructured":"Xin B, Zhang J, Chen J et al (2021) Overview of research on transformation of multi-AUV formations. Complex Syst Modeling Simul 1:1\u201314. https:\/\/doi.org\/10.23919\/CSMS.2021.0003","journal-title":"Complex Syst Modeling Simul"},{"key":"10261_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-023-10620-2","volume":"57","author":"X Wang","year":"2023","unstructured":"Wang X, Wang Y, Su X et al (2023) Deep reinforcement learning-based air combat maneuver decision-making: literature review, implementation tutorial and future direction. Artif Intell Rev 57:1. https:\/\/doi.org\/10.1007\/s10462-023-10620-2","journal-title":"Artif Intell Rev"},{"issue":"4","key":"10261_CR3","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1109\/TAC.1965.1098197","volume":"10","author":"Y Ho","year":"1965","unstructured":"Ho Y, Bryson A, Baron S (1965) Differential games and optimal pursuit-evasion strategies. IEEE Trans Autom Control 10(4):385\u2013389","journal-title":"IEEE Trans Autom Control"},{"key":"10261_CR4","doi-asserted-by":"publisher","first-page":"3423","DOI":"10.1016\/j.cja.2020.03.026","volume":"33","author":"T Yan","year":"2020","unstructured":"Yan T, Cai Y, Xu B (2020) Evasion guidance algorithms for air-breathing hypersonic vehicles in three-player pursuit-evasion games. Chin J Aeronaut 33:3423\u20133436. https:\/\/doi.org\/10.1016\/j.cja.2020.03.026","journal-title":"Chin J Aeronaut"},{"key":"10261_CR5","doi-asserted-by":"crossref","unstructured":"Bao Fu F, Qi Shu P, Bing Rong H (2012) Research on high-speed evader vs. multi-lower speed pursuers in multi pursuit-evasion games. Inf Technol J 11(8): 989","DOI":"10.3923\/itj.2012.989.997"},{"key":"10261_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2021.107491","volume":"96","author":"C Liu","year":"2021","unstructured":"Liu C, Sun S, Tao C et al (2021) Sliding mode control of multi-agent system with application to UAV air combat. Comput Electr Eng 96:107491. https:\/\/doi.org\/10.1016\/j.compeleceng.2021.107491","journal-title":"Comput Electr Eng"},{"key":"10261_CR7","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/JAS.2015.7032901","volume":"2","author":"H Duan","year":"2015","unstructured":"Duan H, Li P, Yu Y (2015) A predator-prey particle swarm optimization approach to multiple UCAV air combat modeled by dynamic game theory. IEEE\/CAA J Automatica Sinica 2:11\u201318. https:\/\/doi.org\/10.1109\/JAS.2015.7032901","journal-title":"IEEE\/CAA J Automatica Sinica"},{"key":"10261_CR8","doi-asserted-by":"publisher","first-page":"11624","DOI":"10.1109\/ACCESS.2019.2933022","volume":"8","author":"Y Ma","year":"2020","unstructured":"Ma Y, Wang G, Hu X et al (2020) Cooperative occupancy decision making of multi-UAV in beyond-visual-range air combat: a game theory approach. IEEE Access 8:11624\u201311634. https:\/\/doi.org\/10.1109\/ACCESS.2019.2933022","journal-title":"IEEE Access"},{"issue":"3","key":"10261_CR9","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.dt.2021.01.005","volume":"18","author":"S Li","year":"2022","unstructured":"Li S, Chen M, Wang Y, Wu Q (2022) Air combat decision-making of multiple UCAVs based on constraint strategy games. Defense Technology 18(3):368\u2013383","journal-title":"Defense Technology"},{"key":"10261_CR10","doi-asserted-by":"publisher","first-page":"1102","DOI":"10.4028\/www.scientific.net\/AMM.494-495.1102","volume":"494\u2013495","author":"X Chen","year":"2014","unstructured":"Chen X, Wang YF (2014) Study on multi-UAV air combat game based on fuzzy strategy. Appl Mech Mater 494\u2013495:1102\u20131105. https:\/\/doi.org\/10.4028\/www.scientific.net\/AMM.494-495.1102","journal-title":"Appl Mech Mater"},{"key":"10261_CR11","doi-asserted-by":"crossref","unstructured":"Chen X, Zhao M (2012) The decision method research on air combat game based on uncertain interval information. In: 2012 Fifth international symposium on computational intelligence and design, pp 456\u2013459","DOI":"10.1109\/ISCID.2012.120"},{"issue":"01","key":"10261_CR12","first-page":"2167","volume":"06","author":"N Ernest","year":"2016","unstructured":"Ernest N, Carroll D (2016) Genetic fuzzy based artificial intelligence for unmanned combat aerial vehicle control in simulated air combat missions. J Def Manag 06(01):2167\u20132374","journal-title":"J Def Manag"},{"key":"10261_CR13","doi-asserted-by":"crossref","unstructured":"Kang Y, Pu Z, Liu Z, et al (2022) Air-to-air combat tactical decision method based on SIRMs fuzzy logic and improved genetic algorithm. In: Proceedings of 2020 international conference on guidance, navigation and control. Springer, pp 3699\u20133709","DOI":"10.1007\/978-981-15-8155-7_308"},{"key":"10261_CR14","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1016\/S1000-9361(11)60188-X","volume":"16","author":"J Gao","year":"2003","unstructured":"Gao J, Tong M (2003) Extracting decision rules for cooperative team air combat based on rough set theory. Chin J Aeronaut 16:223\u2013228. https:\/\/doi.org\/10.1016\/S1000-9361(11)60188-X","journal-title":"Chin J Aeronaut"},{"key":"10261_CR15","doi-asserted-by":"publisher","unstructured":"Changqiang H, Kangsheng D, Hanqiao H, et al (2018) Autonomous air combat maneuvering decision using Bayesian infer-ence and moving horizon optimization. J Syst Eng Electron 29:86\u201397. https:\/\/doi.org\/10.21629\/JSEE.2018.01.09","DOI":"10.21629\/JSEE.2018.01.09"},{"key":"10261_CR16","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.swevo.2012.03.003","volume":"6","author":"MC Su","year":"2012","unstructured":"Su MC, Lai SC, Lin SC, You LF (2012) A new approach to multi-aircraft air combat assignments. Swarm Evol Comput 6:39\u201346. https:\/\/doi.org\/10.1016\/j.swevo.2012.03.003","journal-title":"Swarm Evol Comput"},{"key":"10261_CR17","unstructured":"McGrew JS (2008) Real-time maneuvering decisions for autonomous air combat. Dissertation. Massachusetts Institute of Technology. https:\/\/dspace.mit.edu\/handle\/1721.1\/44927"},{"key":"10261_CR18","doi-asserted-by":"crossref","unstructured":"Sprinkle J, Eklund JM, Kim HJ, Sastry S (2004) Encoding aerial pursuit\/evasion games with fixed wing aircraft into a nonlinear model predictive tracking controller. In: 2004 43rd IEEE conference on decision and control (CDC). IEEE, pp 2609\u20132614","DOI":"10.1109\/CDC.2004.1428851"},{"key":"10261_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104112","volume":"98","author":"Z Sun","year":"2021","unstructured":"Sun Z, Piao H, Yang Z et al (2021) Multi-agent hierarchical policy gradient for Air Combat Tactics emergence via self-play. Eng Appl Artif Intell 98:104112. https:\/\/doi.org\/10.1016\/j.engappai.2020.104112","journal-title":"Eng Appl Artif Intell"},{"key":"10261_CR20","doi-asserted-by":"publisher","first-page":"5417","DOI":"10.1109\/TSMC.2023.3270444","volume":"53","author":"J Chai","year":"2023","unstructured":"Chai J, Chen W, Zhu Y et al (2023) A hierarchical deep reinforcement learning framework for 6-DOF UCAV air-to-ai-r combat. IEEE Trans Syst Man Cybern Syst 53:5417\u20135429. https:\/\/doi.org\/10.1109\/TSMC.2023.3270444","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"10261_CR21","doi-asserted-by":"publisher","unstructured":"Jiandong Z, Qiming Y, Guoqing S, et al (2021) UAV cooperative air combat maneuver decision based on multi-agent reinf-orcement learning. J Syst Eng Electron 32:1421\u20131438. https:\/\/doi.org\/10.23919\/JSEE.2021.000121","DOI":"10.23919\/JSEE.2021.000121"},{"key":"10261_CR22","doi-asserted-by":"publisher","first-page":"563","DOI":"10.3390\/aerospace9100563","volume":"9","author":"X Liu","year":"2022","unstructured":"Liu X, Yin Y, Su Y, Ming R (2022) A multi-UCAV cooperative decision-making method based on an MAPPO algorithm for beyond-visual-range air combat. Aerospace 9:563. https:\/\/doi.org\/10.3390\/aerospace9100563","journal-title":"Aerospace"},{"key":"10261_CR23","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s43684-021-00013-z","volume":"1","author":"L Wang","year":"2021","unstructured":"Wang L, Hu J, Xu Z, Zhao C (2021) Autonomous maneuver strategy of swarm air combat based on DDPG. Auton Intell Syst 1:15. https:\/\/doi.org\/10.1007\/s43684-021-00013-z","journal-title":"Auton Intell Syst"},{"key":"10261_CR24","doi-asserted-by":"crossref","unstructured":"Han Y, Piao H, Hou Y, et al (2022) Deep relationship graph reinforcement learning for multi-aircraft air combat. In: 2022 international joint conference on neural networks (IJCNN), IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN55064.2022.9892208"},{"key":"10261_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119285","volume":"215","author":"H Piao","year":"2023","unstructured":"Piao H, Han Y, Chen H et al (2023) Complex relationship graph abstraction for autonomous air combat collaboration: a le-arning and expert knowledge hybrid approach. Expert Syst Appl 215:119285. https:\/\/doi.org\/10.1016\/j.eswa.2022.119285","journal-title":"Expert Syst Appl"},{"key":"10261_CR26","doi-asserted-by":"publisher","first-page":"19765","DOI":"10.1007\/s00521-023-08784-7","volume":"35","author":"Z Sun","year":"2023","unstructured":"Sun Z, Wu H, Shi Y et al (2023) Multi-agent air combat with two-stage graph-attention communication. Neural Comput Appl 35:19765\u201319781. https:\/\/doi.org\/10.1007\/s00521-023-08784-7","journal-title":"Neural Comput Appl"},{"key":"10261_CR27","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1007\/s11424-024-4029-8","volume":"37","author":"Z Zhao","year":"2024","unstructured":"Zhao Z, Chen J, Xin B et al (2024) Learning scalable task assignment with imperative-priori conflict resolution in Multi-UAV adversarial swarm defense problem. J Syst Sci Complex 37:369\u2013388. https:\/\/doi.org\/10.1007\/s11424-024-4029-8","journal-title":"J Syst Sci Complex"},{"key":"10261_CR28","first-page":"1610","volume":"47","author":"W Shi","year":"2021","unstructured":"Shi W, Feng YH, Cheng GQ et al (2021) Research on multi-aircraft cooperative air combat method based on deep reinforcement learning. Acta Automatica Sinica 47:1610\u20131623","journal-title":"Acta Automatica Sinica"},{"key":"10261_CR29","first-page":"342","volume":"41","author":"C Chen","year":"2020","unstructured":"Chen C, Mo L, Zheng D et al (2020) Cooperative attack-defense game of multiple UAVs with asymmetric maneuverability. Acta Aeronautica et Astronautica Sinica 41:342\u2013354","journal-title":"Acta Aeronautica et Astronautica Sinica"},{"key":"10261_CR30","doi-asserted-by":"crossref","unstructured":"Li S, Chi H, Xie T (2021) Multi-agent combat in non-stationary environments. In: 2021 international joint conference on neural networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN52387.2021.9534036"},{"key":"10261_CR31","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1142\/S2301385023410029","volume":"11","author":"Z Gong","year":"2023","unstructured":"Gong Z, Xu Y, Luo D (2023) UAV cooperative air combat maneuvering confrontation based on multi-agent reinforcement learning. Un Sys 11:273\u2013286. https:\/\/doi.org\/10.1142\/S2301385023410029","journal-title":"Un Sys"},{"key":"10261_CR32","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529:484\u2013489. https:\/\/doi.org\/10.1038\/nature16961","journal-title":"Nature"},{"key":"10261_CR33","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals O, Babuschkin I, Czarnecki WM et al (2019) Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575:350\u2013354. https:\/\/doi.org\/10.1038\/s41586-019-1724-z","journal-title":"Nature"},{"key":"10261_CR34","unstructured":"OpenAI, Berner C, Brockman G, et al (2019) Dota 2 with large scale deep reinforcement learning. https:\/\/arxiv.org\/abs\/191206680"},{"issue":"2","key":"10261_CR35","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","journal-title":"Artif Intell Rev"},{"key":"10261_CR36","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K, et al. (2017) Value-decomposition networks for cooperative multiagent learning. https:\/\/arxiv.org\/abs\/1706.05296"},{"key":"10261_CR37","unstructured":"Rashid T, Samvelyan M, Schroeder C, et al (2018) QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the 35th international conference on machine learning. PMLR, pp 4295\u20134304"},{"key":"10261_CR38","unstructured":"Son K, Kim D, Kang WJ, et al (2019) QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: Proceedings of the 36th international conference on machine learning. PMLR, pp 5887\u20135896"},{"key":"10261_CR39","unstructured":"Wang J, Ren Z, Liu T, et al (2021) QPLEX: duplex dueling multi-agent q-learning. https:\/\/arxiv.org\/abs\/2008.01062"},{"key":"10261_CR40","unstructured":"Yang Y, Luo R, Li M, et al (2018) Mean field multi-agent reinforcement learning. In: Proceedings of the 35th international conference on machine learning. PMLR, pp 5571\u20135580"},{"key":"10261_CR41","unstructured":"Lowe R, Wu Y, Tamar A, et al (2020) Multi-agent actor-critic for mixed cooperative-competitive environments. https:\/\/arxiv.org\/abs\/170602275"},{"key":"10261_CR42","first-page":"24611","volume":"35","author":"C Yu","year":"2022","unstructured":"Yu C, Velu A, Vinitsky E, Gao J, Wang Y, Bayen A, Wu Y (2022) The surprising effectiveness of PPO in cooperative multi-agent games. Adv Neural Inf Process Syst 35:24611\u201324624","journal-title":"Adv Neural Inf Process Syst"},{"key":"10261_CR43","doi-asserted-by":"publisher","first-page":"5886","DOI":"10.1109\/TCOMM.2021.3086535","volume":"69","author":"X Wu","year":"2021","unstructured":"Wu X, Li X, Li J et al (2021) Caching transient content for IoT sensing: multi-agent soft actor-critic. IEEE Trans Commun 69:5886\u20135901. https:\/\/doi.org\/10.1109\/TCOMM.2021.3086535","journal-title":"IEEE Trans Commun"},{"key":"10261_CR44","unstructured":"Schulman J, Wolski F, Dhariwal P, et al (2017) Proximal Policy optimization algorithms. https:\/\/arxiv.org\/abs\/170706347"},{"key":"10261_CR45","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et al (2015) Continuous control with deep reinforcement learning. https:\/\/arxiv.org\/abs\/1509.02971"},{"key":"10261_CR46","unstructured":"Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Proceedings of the 35th international conference on machine learning. PMLR, pp 1861\u20131870"},{"key":"10261_CR47","doi-asserted-by":"crossref","unstructured":"Foerster JN, Farquhar G, Afouras T, et al (2018) Counterfactual multi-agent policy gradients. In: 32nd Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"10261_CR48","unstructured":"Iqbal S, Sha F (2019) Actor-attention-critic for multi-agent reinforcement learning. In: Proceedings of the 36th international conference on machine learning. PMLR, pp 2961\u20132970"},{"key":"10261_CR49","first-page":"26437","volume":"34","author":"Z Wu","year":"2021","unstructured":"Wu Z, Yu C, Ye D et al (2021) Coordinated proximal policy optimization. Adv Neural Inf Process Syst 34:26437\u201326448","journal-title":"Adv Neural Inf Process Syst"},{"key":"10261_CR50","unstructured":"Kuba JG, Chen R, Wen M, et al (2022) Trust region policy optimization in multi-agent reinforcement learning. In: The tenth international conference on learning representations (ICLR)"},{"key":"10261_CR51","unstructured":"Chu X, Ye H (2017) Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning. https:\/\/arxiv.org\/abs\/1710.00336"},{"key":"10261_CR52","unstructured":"Schulman J, Levine S, Moritz P, et al (2015) Trust region policy optimization. In: Proceedings of the 32nd international conference on machine learning, PMLR, pp 1889\u20131897"},{"key":"10261_CR53","doi-asserted-by":"publisher","first-page":"12597","DOI":"10.1109\/TVT.2020.3026111","volume":"69","author":"Y Guan","year":"2020","unstructured":"Guan Y, Ren Y, Li SE et al (2020) Centralized cooperation for connected and automated vehicles at intersections by pro-ximal policy optimization. IEEE Trans Veh Technol 69:12597\u201312608. https:\/\/doi.org\/10.1109\/TVT.2020.3026111","journal-title":"IEEE Trans Veh Technol"},{"key":"10261_CR54","doi-asserted-by":"publisher","first-page":"10239","DOI":"10.1007\/s00521-023-08232-6","volume":"35","author":"L Li","year":"2023","unstructured":"Li L, Zhang X, Qian C, Wang R (2023) Basic flight maneuver generation of fixed-wing plane based on proximal policy optimization. Neural Comput Appl 35:10239\u201310255. https:\/\/doi.org\/10.1007\/s00521-023-08232-6","journal-title":"Neural Comput Appl"},{"issue":"3","key":"10261_CR55","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1049\/itr2.12286","volume":"17","author":"L Huang","year":"2023","unstructured":"Huang L, Qu X (2023) Improving traffic signal control operations using proximal policy optimization. IET Intel Transport Syst 17(3):592\u2013605","journal-title":"IET Intel Transport Syst"},{"key":"10261_CR56","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1515\/9781400840601-010","volume-title":"Small unmanned aircraft theory and practice","author":"RW Beard","year":"2012","unstructured":"Beard RW, McLain TW (2012) Chapter 9. Small unmanned aircraft theory and practice. Princeton University Press, New Jersey, NJ, pp 164\u2013173"},{"key":"10261_CR57","unstructured":"Schulman J, Moritz P, Levine S, et al (2015) High-dimensional continuous control using generalized advantage estimation. https:\/\/arxiv.org\/abs\/1506.02438"},{"key":"10261_CR58","doi-asserted-by":"publisher","first-page":"6672","DOI":"10.1609\/aaai.v34i04.6144","volume":"34","author":"D Ye","year":"2020","unstructured":"Ye D, Liu Z, Sun M et al (2020) Mastering complex control in MOBA games with deep reinforcement learning. Proc AAAI Conf Artif Intell 34:6672\u20136679. https:\/\/doi.org\/10.1609\/aaai.v34i04.6144","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"10261_CR59","unstructured":"Gaertner U (2013) UAV Swarm tactics: an agent-based simulation and markov process analysis. Dissertation, Naval Postgraduate School Monterey Ca Dept of Operations Research"},{"key":"10261_CR60","doi-asserted-by":"publisher","unstructured":"Park S, Deyst J, How J (2004) A new nonlinear guidance logic for trajectory tracking In: AIAA guidance, navigation, and control conference. https:\/\/doi.org\/10.2514\/6.2004-4900","DOI":"10.2514\/6.2004-4900"},{"key":"10261_CR61","unstructured":"Liang E, Liaw R, Moritz P, et al (2018) RLlib: abstractions for distributed reinforcement learning. In: Proceedings of the 35th international conference on machine learning(ICML). PMLR, pp 3053\u20133062"},{"key":"10261_CR62","unstructured":"De Witt CS, Gupta T, Makoviichuk D, et al (2020) Is independent learning all you need in the starcraft multi-agent challenge? https:\/\/arxiv.org\/abs\/2011.09533"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10261-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10261-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10261-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,27]],"date-time":"2024-09-27T12:08:51Z","timestamp":1727438931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10261-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,7]]},"references-count":62,"journal-issue":{"issue":"31","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10261"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10261-8","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,7]]},"assertion":[{"value":"29 September 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 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"}}]}}