{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:37:51Z","timestamp":1772725071340,"version":"3.50.1"},"reference-count":46,"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-nc-nd\/4.0\/"}],"funder":[{"name":"HAVELSAN\u2019s Education Technologies Department"},{"name":"Forces in Virtual Environments Machine Learning (FIVE-ML) project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3573419","type":"journal-article","created":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T18:04:18Z","timestamp":1748282658000},"page":"96544-96563","source":"Crossref","is-referenced-by-count":3,"title":["Strategic Implementation of Super-Agents in Heterogeneous Multi-Agent Training for Advanced Military Simulation Adaptability"],"prefix":"10.1109","volume":"13","author":[{"given":"H\u00fcseyin Oktay","family":"Altun","sequence":"first","affiliation":[{"name":"Institute for Data Science and Artificial Intelligence, Boğaziçi University, Istanbul, Türkiye"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2169-4680","authenticated-orcid":false,"given":"H\u00fcseyin","family":"Furkan Ceran","sequence":"additional","affiliation":[{"name":"HAVELSAN, Çankaya, Ankara, Türkiye"}]},{"given":"Korkut","family":"Kutay Met\u0131n","sequence":"additional","affiliation":[{"name":"HAVELSAN, Çankaya, Ankara, Türkiye"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3015-0910","authenticated-orcid":false,"given":"Tolga","family":"Erol","sequence":"additional","affiliation":[{"name":"HAVELSAN, Çankaya, Ankara, Türkiye"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9196-7398","authenticated-orcid":false,"given":"Emre","family":"Fi\u015fne","sequence":"additional","affiliation":[{"name":"Institute for Data Science and Artificial Intelligence, Boğaziçi University, Istanbul, Türkiye"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Militaries Behind in Applying AI to Training, Simulations","author":"Magnuson","year":"2025"},{"key":"ref2","volume-title":"U.S. Army to Pursue AI and Machine Learning Integration","author":"Hill","year":"2025"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2478\/raft-2021-0022"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10070871"},{"key":"ref5","volume-title":"DARPA is Funding AI to Help Make Battlefield Decisions","author":"Phelan","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/14751798.2022.2031692"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.7249\/rr4311"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.32473\/flairs.v35i.130577"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/21642583.2022.2074169"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/wsc.2003.1261517"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/e24101440"},{"key":"ref12","first-page":"1","article-title":"Heterogeneous swarming for collaborative combat using multi-agent deep reinforcement learning","volume-title":"Proc. Conf. Artif. Intell.","author":"Bois"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2023.10.1431"},{"key":"ref14","volume-title":"U.S. Army Artificial Intelligence Innovation Institute (A2I2) Aiding Multi-Domain Operations (MDO)","author":"Stanton","year":"2020"},{"key":"ref15","article-title":"Heterogeneous multi-robot reinforcement learning","author":"Bettini","year":"2023","journal-title":"arXiv:2301.07137"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/SICE56594.2022.9905866"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3527448"},{"key":"ref18","first-page":"529","article-title":"Simulating teamwork and information flow in tactical operations centers using multi-agent systems","volume-title":"Proc. 10th Conf. Comput. Generated Forces Behav. Represent.","author":"Zhang"},{"key":"ref19","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024","journal-title":"arXiv:2408.09675"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref22","first-page":"4596","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learning. PMLR","volume":"139","author":"Iqbal"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref24","first-page":"17913","article-title":"Pessimism meets invariance: Provably efficient offline mean-field multi-agent RL","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref25","article-title":"Cooperative multi-agent transfer learning with level-adaptive credit assignment","author":"Zhou","year":"2021","journal-title":"arXiv:2106.00517"},{"key":"ref26","first-page":"139","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Christianos"},{"key":"ref27","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","author":"Long","year":"2020","journal-title":"arXiv:2003.10423"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"ref29","first-page":"459","article-title":"PIC: Permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Liu"},{"key":"ref30","first-page":"16509","article-title":"MAG-GNN: Reinforcement learning boosted graph neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kong"},{"key":"ref31","first-page":"16509","article-title":"Multi-agent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref32","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","author":"Hu","year":"2021","journal-title":"arXiv:2101.08001"},{"key":"ref33","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"issue":"178","key":"ref34","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":"ref35","first-page":"563","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son"},{"key":"ref36","first-page":"1","article-title":"Distilling policy distillation","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Czarnecki"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3472473"},{"key":"ref38","first-page":"1","article-title":"IMP-MARL: A suite of environments for large-scale infrastructure management planning via MARL","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Leroy"},{"key":"ref39","article-title":"A review of cooperation in multi-agent learning","author":"Du","year":"2023","journal-title":"arXiv:2312.05162"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"},{"key":"ref41","first-page":"101","article-title":"Enhancing military operations through AI and battlefield digital twin: Integrating Bayesian optimization, genetic algorithms, and reinforcement learning","volume-title":"Proc. STO-MP-MSG","author":"Kim"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.14429\/dsj.74.18864"},{"key":"ref43","article-title":"Symmetric (optimistic) natural policy gradient for multi-agent learning with parameter convergence","author":"Pattathil","year":"2023","journal-title":"arXiv:2210.12812"},{"issue":"2","key":"ref44","first-page":"789","article-title":"Multi-agent reinforcement learning via Lyapunov-based soft actor-critic","volume":"50","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Cybern."},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3011351"},{"key":"ref46","article-title":"Decentralized multi-agent safe reinforcement learning with Lyapunov conditions","author":"Pan","year":"2022","journal-title":"IEEE Robot. Autom. Lett."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11015435.pdf?arnumber=11015435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:26:16Z","timestamp":1749270376000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11015435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3573419","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}