{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:15:17Z","timestamp":1767183317203,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,7,18]],"date-time":"2021-07-18T00:00:00Z","timestamp":1626566400000},"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":[],"published-print":{"date-parts":[[2021,7,18]]},"DOI":"10.1109\/ijcnn52387.2021.9533636","type":"proceedings-article","created":{"date-parts":[[2021,9,20]],"date-time":"2021-09-20T21:27:41Z","timestamp":1632173261000},"page":"1-7","source":"Crossref","is-referenced-by-count":8,"title":["MMD-MIX: Value Function Factorisation with Maximum Mean Discrepancy for Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Zhiwei","family":"Xu","sequence":"first","affiliation":[{"name":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}]},{"given":"Dapeng","family":"Li","sequence":"additional","affiliation":[{"name":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}]},{"given":"Yunpeng","family":"Bai","sequence":"additional","affiliation":[{"name":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}]},{"given":"Guoliang","family":"Fan","sequence":"additional","affiliation":[{"name":"Fusion Innovation Center, Institute of Automation, Chinese Academy of Sciences School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}]}],"member":"263","reference":[{"key":"ref30","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref10","article-title":"An optimistic perspective on offline reinforcement learning","author":"agarwal","year":"2020","journal-title":"ICML"},{"key":"ref11","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"NIPS"},{"key":"ref12","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume":"abs 1605 6676","author":"foerster","year":"2016","journal-title":"ArXiv"},{"key":"ref13","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play starcraft combat games","author":"peng","year":"2017","journal-title":"arXiv Artificial Intelligence"},{"key":"ref14","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"2018","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Learning to schedule communication in multi-agent reinforcement learning","volume":"abs 1902 1554","author":"kim","year":"2019","journal-title":"ArXiv"},{"key":"ref16","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"abs 1706 2275","author":"lowe","year":"2017","journal-title":"ArXiv"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11794","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"AAAI"},{"key":"ref18","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"ICML"},{"key":"ref19","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2018","journal-title":"AAMAS"},{"key":"ref28","article-title":"Mmd gan: Towards deeper understanding of moment matching network","volume":"abs 1705 8584","author":"li","year":"2017","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461096"},{"key":"ref27","article-title":"Generative moment matching networks","volume":"abs 1502 2761","author":"li","year":"2015","journal-title":"ArXiv"},{"key":"ref3","article-title":"Solving rubik's cube with a robot hand","volume":"abs 1910 7113","author":"openai","year":"2019","journal-title":"ArXiv"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11791","article-title":"Distributional reinforcement learning with quantile regression","author":"dabney","year":"2018","journal-title":"AAAI"},{"key":"ref29","article-title":"Auto-encoding variational bayes","volume":"abs 1312 6114","author":"kingma","year":"2014","journal-title":"CoRR"},{"key":"ref5","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"ICML"},{"key":"ref8","article-title":"Fully parameterized quantile function for distributional reinforcement learning","author":"yang","year":"2019","journal-title":"NeurIPS"},{"key":"ref7","article-title":"Implicit quantile networks for distributional reinforcement learning","volume":"abs 1806 6923","author":"dabney","year":"2018","journal-title":"ArXiv"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","volume":"abs 1312 5602","author":"mnih","year":"2013","journal-title":"ArXiv"},{"key":"ref9","article-title":"Distributional reinforcement learning with maximum mean discrepancy","volume":"abs 2007 12354","author":"nguyen","year":"2020","journal-title":"ArXiv"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1109\/TNN.2004.842673","article-title":"Reinforcement learning: An introduction","volume":"16","author":"sutton","year":"2005","journal-title":"IEEE Transactions on Neural Networks"},{"key":"ref20","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"abs 1803 11485","author":"rashid","year":"2018","journal-title":"ArXiv"},{"key":"ref22","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume":"abs 1905 5408","author":"son","year":"2019","journal-title":"ArXiv"},{"key":"ref21","article-title":"Hypernetworks","volume":"abs 1609 9106","author":"ha","year":"2017","journal-title":"ArXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref23","article-title":"The StarCraft Multi-Agent Challenge","volume":"abs 1902 4043","author":"samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref26","article-title":"A kernel method for the two-sample-problem","volume":"abs 805 2368","author":"gretton","year":"2006","journal-title":"ArXiv"},{"key":"ref25","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"gretton","year":"2012","journal-title":"J Mach Learn Res"}],"event":{"name":"2021 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2021,7,18]]},"location":"Shenzhen, China","end":{"date-parts":[[2021,7,22]]}},"container-title":["2021 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9533266\/9533267\/09533636.pdf?arnumber=9533636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T19:46:50Z","timestamp":1673293610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9533636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,18]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn52387.2021.9533636","relation":{},"subject":[],"published":{"date-parts":[[2021,7,18]]}}}