{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,23]],"date-time":"2025-04-23T05:30:38Z","timestamp":1745386238537,"version":"3.37.3"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,1]],"date-time":"2024-06-01T00:00:00Z","timestamp":1717200000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,6]]},"DOI":"10.1109\/tg.2023.3272386","type":"journal-article","created":{"date-parts":[[2023,5,2]],"date-time":"2023-05-02T22:11:09Z","timestamp":1683065469000},"page":"352-364","source":"Crossref","is-referenced-by-count":5,"title":["Cooperative Multiagent Transfer Learning With Coalition Pattern Decomposition"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6375-5206","authenticated-orcid":false,"given":"Tianze","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0406-1922","authenticated-orcid":false,"given":"Fubiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Aerospace Engineering, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Shao","sequence":"additional","affiliation":[{"name":"Noah's Ark Laboratory, Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zipeng","family":"Dai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3026-5240","authenticated-orcid":false,"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Noah's Ark Laboratory, Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhan","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiaotong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weixun","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0267-3749","authenticated-orcid":false,"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Noah's Ark Laboratory, Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong","family":"Li","sequence":"additional","affiliation":[{"name":"Noah's Ark Laboratory, Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wulong","family":"Liu","sequence":"additional","affiliation":[{"name":"Noah's Ark Laboratory, Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"Noah's Ark Laboratory, Huawei, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Mach. Learn. Res.","volume":"80","author":"Haarnoja","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2019.xv.011"},{"key":"ref3","first-page":"1","article-title":"Pommerman: A multi-agent playground","volume-title":"Proc. CoRR","author":"Resnick","year":"2018"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3146858"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3121546"},{"key":"ref7","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref8","first-page":"10757","article-title":"Multi-agent determinantal Q-learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Yang","year":"2020"},{"key":"ref9","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc NeurlPS","author":"Mahajan","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6221"},{"key":"ref12","first-page":"1","article-title":"UPDeT: Universal multi-agent reinforcement learning via policy decoupling with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888905000317"},{"key":"ref15","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kitaev"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3163771"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3144791"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref20","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume-title":"Proc. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"},{"issue":"1","key":"ref21","first-page":"7234","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Mach. Learn. Res.","volume":"21","author":"Rashid","year":"2020"},{"key":"ref22","first-page":"1","article-title":"Hypernetworks","volume-title":"Proc CoRR","author":"Ha","year":"2016"},{"key":"ref23","first-page":"1","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","volume-title":"Proc. CoRR","author":"Yang","year":"2020"},{"key":"ref24","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Mach. Learn. Res.","author":"Wang","year":"2021"},{"key":"ref25","first-page":"17037","article-title":"An efficient transfer learning framework for multiagent reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Yang","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3147221"},{"key":"ref27","first-page":"1","article-title":"Policy distillation","volume-title":"Proc. Mach. Learn. Res.","author":"Rusu","year":"2016"},{"key":"ref28","first-page":"1","article-title":"Evolutionary population curriculum for scaling multi-agent reinforcement learning","volume-title":"Proc. Mach. Learn. Res.","author":"Long","year":"2020"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29946-9_25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00036-3"},{"key":"ref34","first-page":"1","article-title":"Categorical reparameterization with Gumbel-softmax","volume-title":"Proc. Mach. Learn. Res.","author":"Jang","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/0713041"},{"key":"ref36","first-page":"1","article-title":"Action semantics network: Considering the effects of actions in multiagent systems","volume-title":"Proc. Mach. Learn. Res.","author":"Wang","year":"2020"},{"key":"ref37","first-page":"1","article-title":"Starcraft II: A new challenge for reinforcement learning","volume-title":"Proc. CoRR","author":"Vinyals","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10559928\/10114566.pdf?arnumber=10114566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T02:29:45Z","timestamp":1733884185000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10114566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6]]},"references-count":39,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tg.2023.3272386","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2024,6]]}}}