{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T21:25:07Z","timestamp":1783286707737,"version":"3.54.6"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206107"],"award-info":[{"award-number":["62206107"]}],"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":["62406127"],"award-info":[{"award-number":["62406127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Intell. Transport. Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tits.2025.3562302","type":"journal-article","created":{"date-parts":[[2025,4,28]],"date-time":"2025-04-28T17:34:55Z","timestamp":1745861695000},"page":"9579-9592","source":"Crossref","is-referenced-by-count":6,"title":["ADAC: Actor-Double-Attention-Critic for Multi-Agent Cooperation in Mixed Cooperative-Competitive Environments"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7464-5889","authenticated-orcid":false,"given":"He","family":"Kong","sequence":"first","affiliation":[{"name":"Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education and the School of Artificial Intelligence, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3224-0928","authenticated-orcid":false,"given":"Qianli","family":"Xing","sequence":"additional","affiliation":[{"name":"Key Laboratory of Symbolic Computation and Knowledge Engineer of Ministry of Education and the College of Computer Science and Technology, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8191-7788","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runliang","family":"Niu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7835-9556","authenticated-orcid":false,"given":"Hechang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4650-2148","authenticated-orcid":false,"given":"Zhiyi","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2697-8093","authenticated-orcid":false,"given":"Yi","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jilin University, Changchun, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-09996-w"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20733"},{"key":"ref3","first-page":"1025","article-title":"Deep implicit coordination graphs for multi-agent reinforcement learning","volume-title":"Proc. 20th Int. Conf. Auto. Agents Multiagent Syst.","author":"Li"},{"key":"ref4","first-page":"22069","article-title":"Learning individually inferred communication for multi-agent cooperation","volume-title":"Proc. 34th Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ding"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref6","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3115240"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3242997"},{"key":"ref9","first-page":"590","article-title":"PIC: Permutation invariant critic for multi-agent deep reinforcement learning","volume-title":"Proc. 3rd Conf. Robot Learn.","author":"Liu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"issue":"39","key":"ref11","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. 31st Conf. Adv. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109436"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114896"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref17","first-page":"1","article-title":"Solving homogeneous and heterogeneous cooperative tasks with greedy sequential execution","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Liu"},{"key":"ref18","first-page":"12619","article-title":"Distributional reward estimation for effective multi-agent deep reinforcement learning","volume-title":"Proc. 36th Adv. Neural Inf. Process. Syst.","volume":"35","author":"Hu"},{"key":"ref19","first-page":"1","article-title":"Learning when to communicate at scale in multiagent cooperative and competitive tasks","volume-title":"Proc. 7th Int. Conf. Learn. Represent.","author":"Singh"},{"key":"ref20","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. 12th Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref22","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-29513-4_31"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01755-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref27","first-page":"1108","article-title":"Modelling the dynamic joint policy of teammates with attention multi-agent DDPG","volume-title":"Proc. 18th Int. Joint Conf. Auto. Agents Multi-Agent Syst.","author":"Mao"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09455-w"},{"key":"ref29","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Iqbal"},{"key":"ref30","first-page":"1","article-title":"Multi-agent graph-attention communication and teaming","volume-title":"Proc. 20th Int. Conf. Auto. Agents Multiagent Syst.","author":"Niu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref32","first-page":"1","article-title":"Graph attention networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Veli\u010dkovi\u0107"},{"key":"ref33","article-title":"Stackelberg decision transformer for asynchronous action coordination in multi-agent systems","author":"Zhang","year":"2023","journal-title":"arXiv:2305.07856"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105506"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/e24040563"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102318"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref41","first-page":"1","article-title":"LDSA: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning","volume-title":"Proc. 36th Conf. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref42","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015","journal-title":"arXiv:1505.00853"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146858"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3146201"},{"key":"ref46","first-page":"1","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","volume-title":"Proc. 8th Int. Conf. Learn. Represent.","author":"Qian"},{"key":"ref47","first-page":"1","article-title":"Categorical reparameterization with gumbel-softmax","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Jang"},{"key":"ref48","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref49","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.2307\/2531616"},{"key":"ref51","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109917"}],"container-title":["IEEE Transactions on Intelligent Transportation Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6979\/11063346\/10979333.pdf?arnumber=10979333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T05:13:02Z","timestamp":1751519582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10979333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tits.2025.3562302","relation":{},"ISSN":["1524-9050","1558-0016"],"issn-type":[{"value":"1524-9050","type":"print"},{"value":"1558-0016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}