{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T07:48:06Z","timestamp":1767772086159,"version":"3.37.3"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T00:00:00Z","timestamp":1658102400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012335","name":"NATIONAL DEFENSE BASIC SCIENTIFIC RESEARCH PROGRAM","doi-asserted-by":"publisher","award":["JCKY2019203C029,JCKY2019-207B022"],"award-info":[{"award-number":["JCKY2019203C029,JCKY2019-207B022"]}],"id":[{"id":"10.13039\/501100012335","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,7,18]]},"DOI":"10.1109\/ijcnn55064.2022.9891942","type":"proceedings-article","created":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T19:56:04Z","timestamp":1664567764000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution"],"prefix":"10.1109","author":[{"given":"Yunpeng","family":"Bai","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Fusion Innovation Center"}]},{"given":"Chen","family":"Gong","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Comprehensive information system research Center"}]},{"given":"Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Fusion Innovation Center"}]},{"given":"Guoliang","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Fusion Innovation Center"}]},{"given":"Xinwen","family":"Hou","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Comprehensive information system research Center"}]},{"given":"Yu","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Comprehensive information system research Center"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep recurrent q-learning for partially observable mdps","author":"hausknecht","year":"0","journal-title":"2015 AAAI Fall Symposium Series"},{"key":"ref38","volume":"31999","author":"bracewell","year":"1986","journal-title":"The Fourier Transform and Its Applications"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1032"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12039"},{"key":"ref31","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"defferrard","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"1025","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref37","volume":"45","author":"berge","year":"1984","journal-title":"Hypergraphs Combinatorics of Finite Sets"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref36"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","author":"oliehoek","year":"2016","journal-title":"A Concise Introduction to Decentralized POMDPs"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/366"},{"key":"ref10","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"papoudakis","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref40","article-title":"Rode: Learning roles to decompose multi-agent tasks","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Value-decomposition networks for cooperative multi-agent learning","volume":"abs 1706 5296","author":"sunehag","year":"2018","journal-title":"ArXiv"},{"key":"ref12","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref13","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref14","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume":"29","author":"sukhbaatar","year":"2016","journal-title":"Advances in Neural Information Processing Sys-tems"},{"key":"ref15","article-title":"Graph convolutional reinforcement learning","author":"jiang","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Qplex: Duplex dueling multi-agent q-learning","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013558"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107637"},{"key":"ref28","article-title":"Graph convolutional value decomposition in multi-agent reinforcement learning","author":"naderializadeh","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428293"},{"key":"ref27","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63823-8_51"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3366486.3366533"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref5","first-page":"1334","article-title":"End-to-end training of deep visuo-motor policies","volume":"17","author":"levine","year":"2016","journal-title":"The Journal of Machine Learning Research"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref9","first-page":"12491","article-title":"Fop: Factorizing optimal joint policy of maximum-entropy multi-agent reinforcement learning","author":"zhang","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref1","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":"ref20","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11537-007-0657-8"},{"key":"ref21","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref24","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","author":"papoudakis","year":"0","journal-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS)"},{"key":"ref41","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","author":"wang","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref23","article-title":"The surprising effectiveness of mappo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref26","first-page":"arxiv-2007","article-title":"Distributional reinforcement learning with maximum mean discrepancy","author":"nguyen","year":"2020","journal-title":"ArXiv e-prints"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533636"}],"event":{"name":"2022 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2022,7,18]]},"location":"Padua, Italy","end":{"date-parts":[[2022,7,23]]}},"container-title":["2022 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9891857\/9889787\/09891942.pdf?arnumber=9891942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T22:57:40Z","timestamp":1667516260000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9891942\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,18]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcnn55064.2022.9891942","relation":{},"subject":[],"published":{"date-parts":[[2022,7,18]]}}}