{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:22:22Z","timestamp":1740100942325,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/cog51982.2022.9893619","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"49-55","source":"Crossref","is-referenced-by-count":2,"title":["LILAC: Learning a Leader for Cooperative Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuqian","family":"Fu","sequence":"first","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China"}]},{"given":"Jiajun","family":"Chai","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China"}]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China"}]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation Chinese Academy of Sciences,Beijing,China"}]}],"member":"263","reference":[{"key":"ref30","first-page":"7611","article-title":"MAVEN: multi-agent variational exploration","author":"mahajan","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"321","article-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms","volume":"325","author":"zhang","year":"0","journal-title":"Springer Publishing"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref12","first-page":"4292","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"80","author":"rashid","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning(ICML)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref14","first-page":"9876","article-title":"ROMA: multi-agent reinforcement learning with emergent roles","volume":"119","author":"wang","year":"2020","journal-title":"Proceedings of the 37 th International Conference on Machine Learning (ICML)"},{"key":"ref15","article-title":"RODE: learning roles to decompose multi-agent tasks","author":"wang","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref16","first-page":"225","article-title":"The leader and his group","author":"hemphill","year":"1949","journal-title":"Bulletin of Educational Research"},{"key":"ref17","article-title":"The StarCraft multi-agent challenge CoRR","volume":"abs 1902 4043","author":"samvelyan","year":"2019"},{"key":"ref18","article-title":"Multi-Agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Neural Information Processing Systems (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref28","article-title":"Emotion recognition from speech with Gaussian mixture models & via boosted GMM","volume":"3","author":"patel","year":"2017","journal-title":"Int J Eng Sci Res"},{"key":"ref4","first-page":"1529","article-title":"Recent progress of deep reinforcement learning: from AlphaGo to AlphaGo Zero","volume":"34","author":"tang","year":"2017","journal-title":"Control Theory & Applications"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-012-0376-5"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAR49639.2020.9107997"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113679"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628682"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jfranklin.2022.06.052"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004395"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207169"},{"key":"ref1","first-page":"701","article-title":"Review of deep reinforcement learning and discussions on the development of computer Go","volume":"33","author":"zhao","year":"2016","journal-title":"Control Theory & Applications"},{"key":"ref20","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"In International Journal of Autonomous Agents and Multi Agent Systems"},{"key":"ref22","article-title":"QPLEX: duplex dueling multi-agent Q-learning","author":"wang","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref21","article-title":"QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume":"97","author":"son","year":"2019","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"journal-title":"The Condensed Wealth of Nations Centre for Independent Studies","year":"2012","author":"butler","key":"ref24"},{"key":"ref23","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","author":"oliehoek","year":"2016","journal-title":"A Concise Introduction to Decentralized POMDPs"}],"event":{"name":"2022 IEEE Conference on Games (CoG)","start":{"date-parts":[[2022,8,21]]},"location":"Beijing, China","end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9893561\/9893544\/09893619.pdf?arnumber=9893619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:25:28Z","timestamp":1665433528000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893619","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}