{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T11:59:02Z","timestamp":1753358342377,"version":"3.37.3"},"reference-count":53,"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"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"am","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":["61702528"],"award-info":[{"award-number":["61702528"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.2997899","type":"journal-article","created":{"date-parts":[[2020,5,27]],"date-time":"2020-05-27T20:31:59Z","timestamp":1590611519000},"page":"99404-99421","source":"Crossref","is-referenced-by-count":17,"title":["Adaptive Learning: A New Decentralized Reinforcement Learning Approach for Cooperative Multiagent Systems"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3307-5490","authenticated-orcid":false,"given":"Meng-Lin","family":"Li","sequence":"first","affiliation":[]},{"given":"Shaofei","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Chen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Fuzzy control: Theory and practice","author":"hampel","year":"2000","journal-title":"Adv Intell Soft Comput"},{"key":"ref38","first-page":"178","article-title":"An analysis of cooperative coevolutionary algorithms","author":"wiegand","year":"2004"},{"key":"ref33","article-title":"A review of cooperative multi-agent deep reinforcement learning","author":"oroojlooyjadid","year":"2019","journal-title":"arXiv 1908 03963"},{"key":"ref32","first-page":"1","article-title":"A survey on deep reinforcement learning","volume":"41","author":"liu","year":"2018","journal-title":"Chin J Comput"},{"key":"ref31","first-page":"1081","article-title":"Survey of multi-agent reinforcement learning in Markov games","volume":"20","author":"song","year":"2005","journal-title":"Control Decis"},{"key":"ref30","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"arXiv 1702 08887"},{"key":"ref37","first-page":"423","article-title":"Theoretical advantages of lenient learners: An evolutionary game theoretic perspective","volume":"9","author":"panait","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-58484-6_269"},{"key":"ref35","first-page":"1","article-title":"An algorithm for distributed reinforcement learning in cooperative multi-agent systems","author":"lauer","year":"2000","journal-title":"Proc 17th Int Conf Mach Learn"},{"key":"ref34","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"arXiv 1702 08887"},{"article-title":"Coordination of independent learners in cooperative Markov games","year":"2009","author":"matignon","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2007.4399095"},{"key":"ref29","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"arXiv 1605 06676"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008942012299"},{"key":"ref1","first-page":"1","article-title":"Multiagent reinforcement learning for multi-robot systems: A survey","author":"yang","year":"2004"},{"key":"ref20","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"arXiv 1605 07736"},{"key":"ref22","first-page":"1601","article-title":"A review of the research progress of reinforcement learning for multi-robot systems","volume":"26","author":"jun","year":"2011","journal-title":"Control Decis"},{"key":"ref21","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":"ref24","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","author":"yang","year":"2020","journal-title":"arXiv 2002 03950"},{"key":"ref23","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":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2014.01.004"},{"key":"ref25","first-page":"2914","article-title":"Lenient learning in independent-learner stochastic cooperative games","volume":"17","author":"wei","year":"2016","journal-title":"J Mach Learn Res"},{"key":"ref50","article-title":"Deep recurrent Q-Learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"arXiv 1507 06527"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2016.7849837"},{"key":"ref53","article-title":"Deep recurrent Q-Learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"arXiv 1507 06527"},{"key":"ref52","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv 1708 04782"},{"key":"ref11","article-title":"Learning multiagent communication with backpropagation","author":"sukhbaatar","year":"2016","journal-title":"arXiv 1605 07736"},{"key":"ref40","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2015","journal-title":"arXiv 1509 06461 [cs]"},{"key":"ref12","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":"ref13","first-page":"259","article-title":"Path planning based on ant colony tsp algorithm","author":"li","year":"2018","journal-title":"Proc 6th China Command Control Conf"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref15","first-page":"172","article-title":"Multiagent cooperation and competition with deep reinforcement learning","volume":"12","author":"ardi","year":"2017","journal-title":"PLoS ONE"},{"key":"ref16","article-title":"OpenAI GYM","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref17","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","author":"yang","year":"2020","journal-title":"arXiv 2002 03939"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref19","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2017","journal-title":"arXiv 1705 08926"},{"key":"ref4","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","author":"claus","year":"1998","journal-title":"Proc Nat Conf Artif Intell"},{"key":"ref3","article-title":"Generative adversarial self-imitation learning","author":"guo","year":"2018","journal-title":"arXiv 1812 00950"},{"key":"ref6","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"arXiv 1803 11485"},{"key":"ref5","first-page":"317","article-title":"Survey of distributed reinforcement learning algorithms in multi-agent systems","volume":"20","author":"zhong","year":"2003","journal-title":"Control Theory Appl"},{"key":"ref8","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"sunehag","year":"2017","journal-title":"arXiv 1706 05296"},{"key":"ref7","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"arXiv 1905 05408"},{"article-title":"GA3C: GPU-based A3C for deep reinforcement learning","year":"2016","author":"babaeizadeh","key":"ref49"},{"key":"ref9","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"arXiv 1902 04043"},{"key":"ref46","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"},{"journal-title":"Uniform Design and Uniform Designs Table","year":"1994","author":"kaitai","key":"ref45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2421338"},{"key":"ref47","article-title":"MAgent: A many-agent reinforcement learning platform for artificial collective intelligence","author":"zheng","year":"2017","journal-title":"arXiv 1712 00600"},{"key":"ref42","article-title":"Fuzzy control system review","author":"al gizi","year":"2013","journal-title":"Int J Sci Eng Res"},{"key":"ref41","first-page":"2613","article-title":"Double Q-learning","author":"hasselt","year":"2010","journal-title":"Advances in Neural Information Processing Systems 23"},{"key":"ref44","first-page":"55","article-title":"Uniformly design the construction of the table and its use table","volume":"4","author":"yishu","year":"1988","journal-title":"Tactical Missile Technology"},{"key":"ref43","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/8948470\/9102277-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09102277.pdf?arnumber=9102277","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:53:37Z","timestamp":1649444017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9102277\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/access.2020.2997899","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}