{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T02:57:06Z","timestamp":1791687426207,"version":"4.3.4"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,5,1]],"date-time":"2021-05-01T00:00:00Z","timestamp":1619827200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921004"],"award-info":[{"award-number":["61921004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1713209"],"award-info":[{"award-number":["U1713209"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61803085"],"award-info":[{"award-number":["61803085"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62041301"],"award-info":[{"award-number":["62041301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/tnnls.2020.2996209","type":"journal-article","created":{"date-parts":[[2020,6,17]],"date-time":"2020-06-17T22:07:22Z","timestamp":1592431642000},"page":"2054-2065","source":"Crossref","is-referenced-by-count":96,"title":["Reinforcement Learning With Task Decomposition for Cooperative Multiagent Systems"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9269-334X","authenticated-orcid":false,"given":"Changyin","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2021-7106","authenticated-orcid":false,"given":"Wenzhang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6737-1381","authenticated-orcid":false,"given":"Lu","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th Symp Oper Syst Design Implement"},{"key":"ref38","first-page":"5867","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","author":"zhang","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref33","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of Pareto dominating policies","volume":"15","author":"van moffaert","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2869462"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761878"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref36","first-page":"46","article-title":"Task decomposition in reinforcement learning","author":"karlsson","year":"1994","journal-title":"Proc AAAI Spring Symp Goal-Driven Learn"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2014.2358639"},{"key":"ref34","first-page":"525","article-title":"Multi-task learning as multi-objective optimization","author":"sener","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4818"},{"key":"ref40","first-page":"807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"nair","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn"},{"key":"ref11","first-page":"8222","article-title":"MAgent: A many-agent reinforcement learning platform for artificial collective intelligence","author":"zheng","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref12","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref14","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc 31th Int Conf Mach Learn"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref16","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"2974","article-title":"Counterfactual multi-agent policy gradients","author":"foerster","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref28","first-page":"2613","article-title":"Double Q-learning","author":"hasselt","year":"2010","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-018-9719-4"},{"key":"ref27","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2013.2293507"},{"key":"ref6","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":"ref29","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1002\/9781118884614","author":"schwartz","year":"2014","journal-title":"Multi-agent Machine Learning A Reinforcement Approach"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2006.887293"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2904277"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811654"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2897847"},{"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":"Proc 17th Int Conf Auto Agents MultiAgent Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273572"},{"key":"ref21","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref24","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume":"70","author":"omidshafiei","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref23","first-page":"5392","article-title":"Hybrid reward architecture for reinforcement learning","author":"van seijen","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9420773\/09119863.pdf?arnumber=9119863","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T14:14:52Z","timestamp":1696256092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9119863\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":40,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2996209","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}