{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:26:03Z","timestamp":1775665563371,"version":"3.50.1"},"reference-count":151,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3580279","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T19:00:12Z","timestamp":1750100412000},"page":"113666-113685","source":"Crossref","is-referenced-by-count":2,"title":["Modeling Air Combat Behavior for Simulation-Based Pilot Training: A Survey of Machine Learning Approaches"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7679-7816","authenticated-orcid":false,"given":"Andreas","family":"Strand","sequence":"first","affiliation":[{"name":"Norwegian Defence Research Establishment (FFI), Kjeller, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8588-1764","authenticated-orcid":false,"given":"Patrick Ribu","family":"Gorton","sequence":"additional","affiliation":[{"name":"Norwegian Defence Research Establishment (FFI), Kjeller, Norway"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7347-8089","authenticated-orcid":false,"given":"Karsten","family":"Brathen","sequence":"additional","affiliation":[{"name":"Norwegian Defence Research Establishment (FFI), Kjeller, Norway"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Computer generated forces","author":"Dompke","year":"2003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/aer.2022.8"},{"key":"ref3","article-title":"Calculated moves","author":"Toubman","year":"2020"},{"key":"ref4","first-page":"12","volume-title":"Fighter Combat","author":"Shaw","year":"1985"},{"key":"ref5","volume-title":"Promise and Reality: Beyond Visual Range (BVR) Air-to-Air Combat","author":"Higby","year":"2005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5220\/0011306600003274"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/lars\/sbr\/wre54079.2021.9605380"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/1548512918823296"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/7678382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22341-0_39"},{"key":"ref11","volume-title":"Securing the Future of Pilot Training and Mission Readiness"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/icuas51884.2021.9476700"},{"key":"ref13","article-title":"Integrating Virtual Reality Into Flight Training","author":"Narayanan","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e14181"},{"key":"ref15","volume-title":"Reshaping the Industry"},{"issue":"1","key":"ref16","first-page":"27","article-title":"Automated intelligent pilots for combat flight simulation","volume":"20","author":"Jones","year":"1999","journal-title":"AI Mag."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3321894"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-100819-063206"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09433-x"},{"key":"ref22","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref23","volume-title":"Trends in Air-to-Air Combat","author":"Stillion","year":"2015"},{"issue":"1","key":"ref24","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"Taylor","year":"2009","journal-title":"J. Mach. Learn. Res."},{"issue":"5","key":"ref25","doi-asserted-by":"crossref","DOI":"10.1145\/3527448","article-title":"Explainable deep reinforcement learning","volume":"55","author":"Vouros","year":"2023","journal-title":"CSUR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/aerospace11060415"},{"key":"ref27","article-title":"Explainability in multi-agent reinforcement learning for air combat tactics","volume":"217","author":"Selmonaj","year":"2024","journal-title":"M&S as Enabler for Digital Transformation in NATO and Nations"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3222143"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1049\/cth2.12413"},{"key":"ref30","first-page":"4190","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. NIPS","author":"Lundberg"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.2514\/1.i011388"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.7249\/rra1473-1"},{"key":"ref33","article-title":"On how simulations can support adaptive thinking in operations planning","volume":"133","author":"Hannay","year":"2015","journal-title":"M&S Support to Operational Tasks Including War Gaming, Logistics, Cyber Defence"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1177\/0954410019889447"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10620-2"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/drones7040236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10090999"},{"key":"ref38","article-title":"Data-driven behavior modeling for computer generated forces","author":"L\u00f8vlid","year":"2017"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.07.004"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/smc.2017.8123163"},{"key":"ref41","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179443"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1613\/jair.613"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247x(65)90154-x"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3257849"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2024.3395626"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1561\/9781680834116"},{"key":"ref49","first-page":"627","article-title":"A reduction of imitation learning and structured prediction to no-regret online learning","volume-title":"Proc. AISTATS","author":"Ross"},{"key":"ref50","first-page":"4572","article-title":"Generative adversarial imitation learning","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-018-0902-9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44874-8"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1201\/9781420011326"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-0447-4"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10121491"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"1","key":"ref57","article-title":"Curriculum learning for reinforcement learning domains","volume":"21","author":"Narvekar","year":"2020","journal-title":"JMLR"},{"key":"ref58","first-page":"1","article-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","volume-title":"Proc. ICLR","author":"Sukhbaatar"},{"key":"ref59","article-title":"Dota 2 with large scale deep reinforcement learning","author":"OpenAI","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref60","first-page":"2917","article-title":"Hierarchical imitation and reinforcement learning","volume-title":"Proc. ICML","author":"Le"},{"key":"ref61","volume-title":"The Promise of Hierarchical Reinforcement Learning"},{"key":"ref62","first-page":"551","article-title":"A visual, object-oriented approach to simulation behavior authoring","volume-title":"Proc. I\/ITSEC","author":"Fu"},{"key":"ref63","first-page":"57","article-title":"Al for automated combatants in a training application","volume-title":"Proc. IE","author":"Cox"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/5.533956"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1142\/s0218213017300010"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113457"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104096"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59614-3_2"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3384\/9789180753678"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/3657814"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/icarcv50220.2020.9305467"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.3390\/e25101409"},{"key":"ref73","article-title":"Air combat maneuvering via operations research and artificial intelligence methods","author":"Crumpacker","year":"2021"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11071-023-08725-y"},{"key":"ref75","article-title":"BVR gym: A reinforcement learning environment for Beyond-Visual-Range air combat","author":"\u0160\u010dukins","year":"2024","journal-title":"arXiv:2403.17533"},{"key":"ref76","article-title":"Data-driven methods for enhanced situation awareness in beyond visual range air combat","author":"\u0160\u010dukins","year":"2025"},{"key":"ref77","article-title":"On the efficiency of transfer learning in a fighter pilot behavior modelling context","author":"Sandstr\u00f6m","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/icuas54217.2022.9836131"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2012.6252763"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992698"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3060426"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0"},{"key":"ref84","first-page":"19","article-title":"Deep self-optimizing artificial intelligence for tactical analysis, training and optimization","volume-title":"Proc. AI4HM","volume":"190","author":"Sommer"},{"key":"ref85","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Lillicrap"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03098-8_2"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20816-9_53"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22341-0_42"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/icmla58977.2023.00153"},{"key":"ref90","article-title":"Tactical simulation in air-to-air combat","author":"Johansson","year":"2018"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/197306"},{"key":"ref92","article-title":"Imitation learning for modelling air combat behaviour","author":"Gorton","year":"2023"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/WSC60868.2023.10408232"},{"key":"ref94","article-title":"Trainable automated forces","volume-title":"Proc. Interservice\/Industry Training, Simulation, Educ. Conf. (I\/ITSEC)","author":"Abbott"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.2514\/1.46815"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2023.3270444"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/cvidl51233.2020.000-7"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.3390\/app122010230"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60135-5_19"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1117\/12.2585530"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.4172\/2167-0374.1000144"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.4271\/2014-01-2174"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1142\/S2301385015500120"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/cog51982.2022.9893690"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892208"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.104112"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn48605.2020.9207088"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.7249\/rr4311"},{"key":"ref109","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. ICML","author":"Duan"},{"key":"ref110","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. ICML","author":"Mnih"},{"key":"ref111","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. NIPS","author":"Lowe"},{"issue":"178","key":"ref112","first-page":"1","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":"ref113","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Haarnoja"},{"issue":"2","key":"ref114","first-page":"154","article-title":"AlphaDogfight trials","volume":"36","author":"DeMay","year":"2022","journal-title":"Johns Hopkins APL Tech. Dig."},{"key":"ref115","volume-title":"ACE Program\u2019s AI Agents Transition From Simulation to Live Flight"},{"key":"ref116","article-title":"Pentagon Takes AI Dogfighting to Next Level in Real-World Flight Tests Against Human F-16 Pilot","author":"Harper","year":"2024","journal-title":"DefenseScoop"},{"key":"ref117","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref118","article-title":"The 37 implementation details of proximal policy optimization","volume-title":"Proc. ICLR Blog Track","author":"Huang"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6205-6"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/access.2024.3406148"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref124","article-title":"Revisiting parameter sharing in multi-agent deep reinforcement learning","author":"Terry","year":"2020","journal-title":"arXiv:2005.13625"},{"key":"ref125","first-page":"26437","article-title":"Coordinated proximal policy optimization","volume-title":"Proc. NeurIPS","author":"Wu"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.2514\/6.2009-5699"},{"key":"ref127","article-title":"Are we machine learning yet? Computer generated forces with learning capabilities in military simulation","volume-title":"Proc. I\/ITSEC","author":"Van Oijen"},{"key":"ref128","volume-title":"Command Modern Operations Game Manual","year":"2023"},{"key":"ref129","volume-title":"Digital Combat Simulator User Manual","year":"2020"},{"key":"ref130","first-page":"16","article-title":"STRIVE: An open and distributed architecture for CGF representations","volume-title":"Proc. 9th CGF BR Conf.","author":"Siksik"},{"key":"ref131","article-title":"Metodiker vid regelskrivning","author":"Johansson","year":"2004"},{"key":"ref132","volume-title":"VBS4 Product Brochure","year":"2024"},{"key":"ref133","article-title":"Game theory and prescriptive analytics for naval wargaming battle management aids","author":"Johnson","year":"2018"},{"key":"ref134","first-page":"843","article-title":"The deployable virtual training environment","volume-title":"Proc. I\/ITSEC","author":"Bailey"},{"key":"ref135","first-page":"73","article-title":"Advanced framework for simulation, integration and modeling (AFSIM)","volume-title":"Proc. CSC","author":"Clive"},{"key":"ref136","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. ICML","author":"Schulman"},{"key":"ref137","first-page":"165","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2016"},{"key":"ref138","first-page":"1","article-title":"Fighter combat-tactical awareness capability (FC-TAC) for use in live virtual constructive training","volume-title":"Proc. Fall Simulation Interoperability Workshop (SIW)","author":"Watz"},{"key":"ref139","first-page":"73","article-title":"Rapid adaptive realistic behavior modeling is viable for use in training","volume-title":"Proc. 23rd Conf. Behav. Represent. Modeling Simulation (BRiMS)","author":"Doyle"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.4172\/2324-9307.1000173"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-22341-0_30"},{"key":"ref142","article-title":"Assessing and selecting AI pilots for tactical and training skill","volume":"177","author":"Freeman","year":"2020","journal-title":"Towards On-Demand Personalized Training and Decision Support"},{"key":"ref143","first-page":"6","article-title":"Readiness product line","volume":"67","author":"Bennett","year":"2022","journal-title":"AFRL Fight\u2019s"},{"key":"ref144","first-page":"12","article-title":"Not so grand challenge (NSGC)","volume":"75","author":"Perry","year":"2024","journal-title":"AFRL Fight\u2019s"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/lars\/sbr\/wre51543.2020.9306947"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ieeestd.2010.5553440"},{"key":"ref147","article-title":"Gymnasium: A standard interface for reinforcement learning environments","author":"Towers","year":"2024","journal-title":"arXiv:2407.17032"},{"key":"ref148","author":"Hua","year":"2023","journal-title":"PyCMO: Command Modern Operations Reinforcement Learning Environment"},{"key":"ref149","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent. ICLR)","author":"Schaul"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11037415.pdf?arnumber=11037415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T04:33:18Z","timestamp":1751689998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11037415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":151,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3580279","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}