{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:44:32Z","timestamp":1768423472277,"version":"3.49.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61973244"],"award-info":[{"award-number":["61973244"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72001214"],"award-info":[{"award-number":["72001214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61573277"],"award-info":[{"award-number":["61573277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3214481","type":"journal-article","created":{"date-parts":[[2022,10,13]],"date-time":"2022-10-13T19:34:06Z","timestamp":1665689646000},"page":"108775-108784","source":"Crossref","is-referenced-by-count":2,"title":["Attentional Factorized Q-Learning for Many-Agent Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3783-1268","authenticated-orcid":false,"given":"Xiaoqiang","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory for Manufacturing Systems Engineering, School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2920-0853","authenticated-orcid":false,"given":"Liangjun","family":"Ke","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Manufacturing Systems Engineering, School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1456-4216","authenticated-orcid":false,"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Air and Missile Defense College, Air Force Engineering University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020","journal-title":"arXiv:2011.00583"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref3","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015410"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref6","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref7","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn. (ICML)","volume":"80","author":"Rashid"},{"key":"ref8","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Son"},{"key":"ref9","first-page":"5567","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","volume":"80","author":"Yang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIBD55127.2022.9820093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3356464.3357707"},{"key":"ref13","first-page":"980","article-title":"Deep coordination graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"B\u00f6hmer"},{"key":"ref14","first-page":"1862","article-title":"The representational capacity of action-value networks for multi-agent reinforcement learning","volume-title":"Proc. 18th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Castellini"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref16","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref17","first-page":"7265","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref18","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref19","first-page":"7301","article-title":"Tesseract: Tensorised actors for multi-agent reinforcement learning","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Mahajan"},{"key":"ref20","first-page":"227","article-title":"Coordinated reinforcement learning","volume-title":"Proc. ICML","volume":"2","author":"Guestrin"},{"key":"ref21","first-page":"482","article-title":"Learning to coordinate with coordination graphs in repeated single-stage multi-agent decision problems","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Bargiacchi"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/b978-1-55860-335-6.50027-1"},{"key":"ref23","article-title":"Tensor and matrix low-rank value-function approximation in reinforcement learning","author":"Rozada","year":"2022","journal-title":"arXiv:2201.09736"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/bf02288367"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/080738970"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tit.2010.2044061"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10311"},{"key":"ref28","first-page":"1704","article-title":"Contextual decision processes with low Bellman rank are PAC-learnable","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2017.2716382"},{"key":"ref30","first-page":"12092","article-title":"Sample efficient reinforcement learning via low-rank matrix estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Shah"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/239"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168771"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-015-0892-3"},{"key":"ref38","first-page":"1","article-title":"Exploiting structure and agent-centric rewards to promote coordination in large multiagent systems","volume-title":"Proc. Adapt. Learn. Agents Workshop.","author":"HolmesParker"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09919180.pdf?arnumber=9919180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T06:33:53Z","timestamp":1706078033000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9919180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3214481","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}