{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:45:25Z","timestamp":1765910725093,"version":"3.48.0"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Open Projects Program of the State Key Laboratory of Multimodal Artificial Intelligence Systems","award":["MAIS2024108"],"award-info":[{"award-number":["MAIS2024108"]}]},{"name":"Big Data Computing Center of Southeast University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tcds.2024.3470068","type":"journal-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T13:30:51Z","timestamp":1727703051000},"page":"465-479","source":"Crossref","is-referenced-by-count":0,"title":["HDMTK: Full Integration of Hierarchical Decision-Making and Tactical Knowledge in Multiagent Adversarial Games"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9235-9429","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"first","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2888-3559","authenticated-orcid":false,"given":"Boling","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"School of Instrument Science and Engineering, Southeast University, Nanjing, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3034-9639","authenticated-orcid":false,"given":"Kaizhu","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Duke Kunshan University, Kunshan, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3110959"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-8155-7_464"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2970487"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1093\/isq\/sqab052"},{"key":"ref5","first-page":"506","article-title":"Air combat autonomous Maneuver decision for one-on-one within visual range engagement base on robust multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Control & Automat.","author":"Weiren","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA58977.2023.00153"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893656"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3236065"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.05.090"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.12783\/dtcse\/cisnr2020\/35167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21629\/JSEE.2018.01.09"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-03098-8_2"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/app13074569"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2023.01.009"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3022638"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5220\/0011747900003411"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3266791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191422"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3296166"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9101668"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3222143"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCSI53130.2021.9736221"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11741"},{"key":"ref25","first-page":"1922","article-title":"Landmark based reward shaping in reinforcement learning with hidden states","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst.","author":"Demir","year":"2019"},{"key":"ref26","first-page":"1407","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Li","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CCWC57344.2023.10099211"},{"key":"ref28","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume-title":"Proc. Int. Conf. Autonomous Agents Multiagent Syst.","author":"Sunehag","year":"2018"},{"issue":"1","key":"ref29","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":"ref30","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":"ref31","first-page":"32438","article-title":"Rethinking individual global max in cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hong","year":"2022"},{"key":"ref32","first-page":"651","article-title":"Air combat strategies generation of CGF based on MADDPG and reward shaping","volume-title":"Proc. Int. Conf. Comput. Vis., Image Deep Learn.","author":"Weiren","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/isec_a_00425"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"article-title":"Understanding multi-step deep reinforcement learning: A systematic study of the DQN target","year":"2019","author":"Hernandez-Garcia","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/3360116"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref38","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","year":"2021","author":"Hu","key":"ref39"},{"issue":"3","key":"ref40","first-page":"755","article-title":"Multi-agent decision-making method based on Actor-Critic framework and its application in wargame","volume":"43","author":"Chen","year":"2021","journal-title":"Syst. Eng. Electron."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-89370-5_7"},{"key":"ref42","first-page":"4405","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Du","year":"2019"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3263013"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11023974\/10697976.pdf?arnumber=10697976","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:32:59Z","timestamp":1765909979000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10697976\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":43,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2024.3470068","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}