{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T20:11:03Z","timestamp":1780517463449,"version":"3.54.1"},"reference-count":71,"publisher":"Tsinghua University Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int. J. Crowd Sci."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.26599\/ijcs.2024.9100027","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T20:10:09Z","timestamp":1780431009000},"page":"94-105","source":"Crossref","is-referenced-by-count":0,"title":["Overview of Intelligent Game: From Game AI to Military Combat Simulation"],"prefix":"10.26599","volume":"10","author":[{"given":"Wanpeng","family":"Ma","sequence":"first","affiliation":[{"name":"Army Aviation Institute,Beijing,China,101121"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Xiao","sequence":"additional","affiliation":[{"name":"Army Aviation Institute,Beijing,China,101121"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liping","family":"Wang","sequence":"additional","affiliation":[{"name":"Army Aviation Institute,Beijing,China,101121"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaojie","family":"Lv","sequence":"additional","affiliation":[{"name":"Army Aviation Institute,Beijing,China,101121"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoting","family":"Sun","sequence":"additional","affiliation":[{"name":"Army Aviation Institute,Beijing,China,101121"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiancheng","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering, Xi'an Jiaotong University,Xi'an,China,710049"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1384-6"},{"key":"ref2","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.orp.2021.100204"},{"key":"ref4","first-page":"28162","article-title":"Mastering the game of No-press Diplomacy via human-regularized reinforcement learning and planning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bakhtin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.aao1733"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay7774"},{"key":"ref10","article-title":"DecisionHoldem: Safe depth-limited solving with diverse opponents for imperfect-information games","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","first-page":"12333","article-title":"DouZero: Mastering DouDizhu with self-play deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn., Virtual Event","author":"Zha","year":"2021"},{"issue":"1","key":"ref12","first-page":"145","article-title":"Solving GuanDan poker games with deep reinforcement learning","volume":"61","author":"Ge","year":"2024","journal-title":"J. Comput. Res. Dev."},{"key":"ref13","article-title":"Suphx: Mastering Mahjong with deep reinforcement learning","author":"Li","year":"2020","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref15","first-page":"10905","article-title":"SCC: An efficient deep reinforcement learning agent mastering the game of StarCraft II","volume-title":"Proc. Int. Conf. Mach. Learn., Virtual Event","author":"Wang","year":"2021"},{"key":"ref16","first-page":"133386","article-title":"Large language models play starcraft ii: Benchmarks and a chain of summarization approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref17","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3029475"},{"key":"ref19","first-page":"10649","article-title":"Towards playing full MOBA games with deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Virtual Event","author":"Ye","year":"2020"},{"issue":"9","key":"ref20","first-page":"1871","article-title":"Survey on intelligent wargaming: Tactical & campaign wargame and strategic game from game-theoretic perspective","volume":"35","author":"Luo","year":"2023","journal-title":"J. Syst. Simul."},{"issue":"8","key":"ref21","first-page":"151","article-title":"Research on war game simulation based on multi-agent system","volume":"42","author":"Liu","year":"2021","journal-title":"J. Ordnance Equip. Eng."},{"issue":"1","key":"ref22","first-page":"67","article-title":"Application of intelligent algorithm in military chess antagonism deduction","volume":"43","author":"Tian","year":"2021","journal-title":"Command Control Simul."},{"issue":"20","key":"ref23","first-page":"271","article-title":"Application of deep reinforcement learning algorithm on intelligent military decision system","volume":"57","author":"Kuang","year":"2021","journal-title":"Comput. Eng. Appl."},{"issue":"2","key":"ref24","first-page":"210","article-title":"An knowledge-model embedding reinforcement learning method to task-oriented wargaming contingency planning","volume":"9","author":"Zhang","year":"2023","journal-title":"J. Command Control"},{"issue":"3","key":"ref25","first-page":"301","article-title":"Intelligent wargame deduction decision method based on deep reinforcement learning","volume":"8","author":"Hu","year":"2022","journal-title":"J. Command Control"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961426"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3060426"},{"issue":"4","key":"ref28","first-page":"142","article-title":"UCAV autonomic maneuver decision-making method based on reinforcement learning","volume":"44","author":"Sun","year":"2019","journal-title":"Fire Control Command Control"},{"key":"ref29","first-page":"196","article-title":"Research on intelligent maneuver decision generation of within visual range air combat","volume":"31","author":"Wang","year":"2024","journal-title":"Def. Technol."},{"key":"ref30","volume-title":"Heron Systems\u2019 AI defeats human pilot in US DARPA AlphaDogfight trials","author":"Pat","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3222143"},{"issue":"4","key":"ref32","first-page":"897","article-title":"Research on deep reinforcement learning technology for unmanned aerial vehicle air combat maneuvering decision","volume":"35","author":"Han","year":"2024","journal-title":"J. Syst. Eng. Electron."},{"issue":"8","key":"ref33","first-page":"2487","article-title":"Research on air combat game decision based on deep reinforcement learning","volume":"45","author":"Ma","year":"2023","journal-title":"Syst. Eng. Electron."},{"issue":"11","key":"ref34","first-page":"1498","article-title":"Unmanned aerial vehicles swarm conflict based on multi-agent system","volume":"32","author":"Luo","year":"2015","journal-title":"Control Theory Appl."},{"issue":"1","key":"ref35","first-page":"44","article-title":"Strategic deterrence decision model based on deep learning","volume":"3","author":"Rong","year":"2017","journal-title":"J. Command Control"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993459"},{"issue":"2","key":"ref37","first-page":"1","article-title":"Game confrontation strategy training model for air combat based on multi-agent deep reinforcement learning","volume":"12","author":"Sun","year":"2021","journal-title":"Command Inf. Syst. Technol."},{"issue":"12","key":"ref38","first-page":"3940","article-title":"UAV intelligent attack strategy generation model based on multi-agent game reinforcement learning","volume":"45","author":"Hao","year":"2023","journal-title":"Syst. Eng. Electron."},{"issue":"3","key":"ref39","first-page":"870","article-title":"MARL-based design of multi-unmanned aerial vehicle assisted communication system with hybrid gaming mode","volume":"44","author":"Wu","year":"2022","journal-title":"J. Electron. Inf. Technol."},{"issue":"5","key":"ref40","first-page":"625","article-title":"Pursuit-evasion game decision technology of high speed vehicles","volume":"43","author":"Cui","year":"2022","journal-title":"J. Astronaut."},{"issue":"8","key":"ref41","first-page":"1664","article-title":"Key technologies and development trends in the pursuit-evasion game of intelligent aerial vehicles","volume":"49","author":"Zhao","year":"2023","journal-title":"Acta Autom. Sin."},{"issue":"6","key":"ref42","first-page":"867","article-title":"Intelligent game-maneuvering policy for reentry glide vehicle in diving phase","volume":"44","author":"Jiang","year":"2023","journal-title":"J. Astronaut."},{"issue":"18","key":"ref43","first-page":"228255","article-title":"Cooperative game guidance method for hypersonic vehicles based on reinforcement learning","volume":"44","author":"Ni","year":"2023","journal-title":"Acta Aeronaut. Astronaut. Sin."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace10010086"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace10020133"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2021.100696"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2023.03.014"},{"issue":"4","key":"ref48","first-page":"101","article-title":"Autonomous planning of spacecraft pursuit-evasion maneuver trajectory based on artificial intelligence method","volume":"45","author":"Wu","year":"2023","journal-title":"J. Natl. Univ. Def. Technol."},{"issue":"5","key":"ref49","first-page":"3601","article-title":"Strategy solution of non-cooperative target pursuit-evasion game based on branching deep reinforcement learning","volume":"18","author":"Liu","year":"2022","journal-title":"J. Ind. Manag. Optim."},{"key":"ref50","doi-asserted-by":"crossref","first-page":"108604","DOI":"10.1016\/j.ast.2023.108604","article-title":"Terminal-guidance based reinforcement-learning for orbital pursuit-evasion game of the spacecraft","volume":"139","author":"Geng","year":"2023","journal-title":"Aerosp. Sci. Technol."},{"key":"ref51","first-page":"108955","article-title":"Multi-stage reinforcement learning method for orbital pursuit-evasion game of spacecraft","volume":"146","author":"Yuan","year":"2024","journal-title":"Aerosp. Sci. Technol."},{"issue":"3","key":"ref52","first-page":"345","article-title":"Spacecraft reinforcement learning platform design and orbital countermeasure application","volume":"45","author":"Li","year":"2024","journal-title":"J. Astronaut."},{"issue":"5","key":"ref53","first-page":"1610","article-title":"Research on autonomous evasion task decision-making method for multi-agent system","volume":"46","author":"Yu","year":"2024","journal-title":"Syst. Eng. Electron."},{"issue":"2","key":"ref54","first-page":"91","article-title":"Method for cluster satellite orbit pursuit-evasion game based on multi-agent deep deterministic policy gradient algorithm","volume":"39","author":"Xu","year":"2022","journal-title":"J. Shanghai Aerosp."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.asr.2023.08.043"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3076729"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2962482"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2021.3050645"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref61","first-page":"457","article-title":"Off-policy actor-critic","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Degris"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref63","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"AI and wargaming","author":"Goodman","year":"2020","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.26599\/IJCS.2023.9100023"},{"issue":"2","key":"ref66","first-page":"246","article-title":"Computational experiments: Past, present and perspective","volume":"49","author":"Xue","year":"2023","journal-title":"Acta Autom. Sin."},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123639"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955400"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2019.2939934"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.paerosci.2024.101005"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100593"}],"container-title":["International Journal of Crowd Science"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9736195\/11548555\/11548556.pdf?arnumber=11548556","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T19:46:20Z","timestamp":1780515980000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11548556\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":71,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.26599\/ijcs.2024.9100027","relation":{},"ISSN":["2398-7294"],"issn-type":[{"value":"2398-7294","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}