{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T08:44:57Z","timestamp":1767084297494,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61806221"],"award-info":[{"award-number":["61806221"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Advanced research fund of equipment development department","award":["61421010318"],"award-info":[{"award-number":["61421010318"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3011670","type":"journal-article","created":{"date-parts":[[2020,7,24]],"date-time":"2020-07-24T20:27:57Z","timestamp":1595622477000},"page":"135605-135616","source":"Crossref","is-referenced-by-count":14,"title":["A Novel Multi-Agent Parallel-Critic Network Architecture for Cooperative-Competitive Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8218-3909","authenticated-orcid":false,"given":"Yu","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3608-4985","authenticated-orcid":false,"given":"Jun","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6997-8504","authenticated-orcid":false,"given":"Lei","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5198-0932","authenticated-orcid":false,"given":"Xiliang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0996-436X","authenticated-orcid":false,"given":"Zhixiong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2518-7273","authenticated-orcid":false,"given":"Yue","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.920231"},{"key":"ref38","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","article-title":"Parameter sharing deep deterministic policy gradient for cooperative multi-agent reinforcement learning","author":"chu","year":"2017","journal-title":"arXiv 1710 00336"},{"key":"ref32","article-title":"Multi-agent actor-critic with generative cooperative policy network","author":"ryu","year":"2018","journal-title":"arXiv 1810 09206"},{"key":"ref31","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref30","article-title":"Mean field multi-agent reinforcement learning","author":"yang","year":"2018","journal-title":"arXiv 1802 05438"},{"key":"ref37","article-title":"R-MADDPG for partially observable environments and limited communication","author":"wang","year":"2020","journal-title":"arXiv 2002 06684"},{"key":"ref36","article-title":"Modelling the dynamic joint policy of teammates with attention multi-agent DDPG","author":"mao","year":"2018","journal-title":"arXiv 1811 07029"},{"key":"ref35","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"arXiv 1802 09477"},{"key":"ref34","article-title":"Reducing overestimation bias in multi-agent domains using double centralized critics","author":"ackermann","year":"2019","journal-title":"arXiv 1910 01465"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"key":"ref40","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1007\/978-3-642-21557-5_8","article-title":"Ensemble methods for reinforcement learning with function approximation","author":"fau\u00dfer","year":"2011","journal-title":"Proc Int Workshop Multiple Classifier Syst"},{"key":"ref11","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref14","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2017","journal-title":"arXiv 1710 03748"},{"key":"ref15","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref16","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","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 1703 10069"},{"key":"ref18","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"ACCNet: Actor-coordinator-critic net for ‘learning-to-communicate’ with deep multi-agent reinforcement learning","author":"mao","year":"2017","journal-title":"arXiv 1706 03235"},{"key":"ref28","article-title":"Neighborhood cognition consistent multi-agent reinforcement learning","author":"mao","year":"2019","journal-title":"arXiv 1912 01160"},{"key":"ref4","first-page":"183","article-title":"Multi-agent reinforcement learning: An overview","author":"bu?oniu","year":"2010","journal-title":"Innovations in Multi-Agent Systems and Applications - 1"},{"key":"ref27","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","author":"yang","year":"2020","journal-title":"arXiv 2002 03950"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/PSCE.2009.4840087"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281729"},{"key":"ref29","article-title":"Reward design in cooperative multi-agent reinforcement learning for packet routing","author":"mao","year":"2020","journal-title":"arXiv 2003 03433"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2010.2043124"},{"key":"ref8","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref7","first-page":"322","article-title":"Friend-or-foe Q-learning in general-sum games","author":"littman","year":"2001","journal-title":"Proc ICML"},{"key":"ref2","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":"ref9","first-page":"242","article-title":"Correlated Q-learning","author":"greenwald","year":"2003","journal-title":"Proc Int Conf Int Conf Mach Learn (ICML)"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref20","article-title":"Learning agent communication under limited bandwidth by message pruning","author":"mao","year":"2019","journal-title":"arXiv 1912 05304"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3205326.3205346"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09455-w"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2010.66"},{"key":"ref24","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"arXiv 1803 11485"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1007\/s11063-013-9334-5","article-title":"Neural network ensembles in reinforcement learning","volume":"41","author":"fau\u00dfer","year":"2015","journal-title":"Neural Process Lett"},{"key":"ref23","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc 4th Int Conf Auton Agents Multiagent Syst (AAMAS)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref43","article-title":"EPOpt: Learning robust neural network policies using model ensembles","author":"rajeswaran","year":"2016","journal-title":"arXiv 1610 01283"},{"key":"ref25","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"arXiv 1705 08926"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09146854.pdf?arnumber=9146854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:56:37Z","timestamp":1642002997000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9146854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3011670","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}