{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T04:51:48Z","timestamp":1785387108041,"version":"3.55.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020YFB1804804"],"award-info":[{"award-number":["2020YFB1804804"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61731002"],"award-info":[{"award-number":["61731002"]}],"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":["62071425"],"award-info":[{"award-number":["62071425"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Key Research and Development Plan","award":["2019C01002"],"award-info":[{"award-number":["2019C01002"]}]},{"name":"Zhejiang Key Research and Development Plan","award":["2019C03131"],"award-info":[{"award-number":["2019C03131"]}]},{"DOI":"10.13039\/501100017530","name":"Huawei Cooperation Project, the Project sponsored by Zhejiang Lab","doi-asserted-by":"publisher","award":["2019LC0AB01"],"award-info":[{"award-number":["2019LC0AB01"]}],"id":[{"id":"10.13039\/501100017530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LY20F010016"],"award-info":[{"award-number":["LY20F010016"]}],"id":[{"id":"10.13039\/501100004731","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":[[2022,9]]},"DOI":"10.1109\/tnnls.2021.3056418","type":"journal-article","created":{"date-parts":[[2021,2,16]],"date-time":"2021-02-16T14:58:14Z","timestamp":1613487494000},"page":"4285-4299","source":"Crossref","is-referenced-by-count":30,"title":["Stigmergic Independent Reinforcement Learning for Multiagent Collaboration"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-470X","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"first","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-5060","authenticated-orcid":false,"given":"Rongpeng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5479-7890","authenticated-orcid":false,"given":"Zhifeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1492-1364","authenticated-orcid":false,"given":"Honggang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.03.008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-32259-7_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IISA.2015.7387990"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47745-4_15"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-3615(03)00123-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2006.25"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2016.7402272"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-60240-0_35"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref13","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"arXiv:1602.01783","author":"Mnih","year":"2016"},{"issue":"1","key":"ref14","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","volume":"32","author":"Silver"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/b978-1-55860-335-6.50027-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref18","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"arXiv:1605.06676","author":"Foerster","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref20","article-title":"ACCNet: Actor-coordinator-critic net for \u2018learning-to-communicate\u2019 with deep multi-agent reinforcement learning","volume-title":"arXiv:1706.03235","author":"Mao","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1080\/095281398146806"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2015.12.002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2015.12.007"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700500203"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1613\/jair.530"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-739X(00)00042-X"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CIT.2016.68"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WI-IAT.2012.121"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/VNC.2012.6407442"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913182"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2018.0383"},{"key":"ref32","first-page":"57","article-title":"Multiagent systems: Lessons from social insects and collective robotics","volume-title":"Proc. Adaptation, Coevol. Learn. Multiagent Syst., Papers AAAI Spring Symp.","author":"Holland"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71103-2_7"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2009.2037732"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2006.329691"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082672"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICHIS.2004.87"},{"key":"ref38","article-title":"Stigmergy and bootstrapping: Using ant algorithms as a case study for learning in MAS","volume-title":"Proc. 2nd Int. Workshop Ant Algorithms","author":"Verbeeck"},{"key":"ref39","first-page":"2681","article-title":"Deep decentralized multi-task multi-agent reinforcement learning under partial observability","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","volume":"70","author":"Omidshafiei"},{"key":"ref40","article-title":"Learning policies with external memory","volume-title":"Proc. 16th Int. Conf. Mach. Learn.","author":"Peshkin"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1298091.1298115"},{"issue":"3","key":"ref42","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2002.1049611"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.12.152"},{"issue":"1","key":"ref45","first-page":"71","article-title":"Stochastic gradient descent for non-smooth optimization: Convergence results and optimal averaging schemes","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","volume":"28","author":"Shamir"},{"key":"ref46","article-title":"Large scale distributed deep networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Dean"},{"key":"ref47","article-title":"Concentrated differentially private and utility preserving federated learning","volume-title":"arXiv:2003.13761","author":"Hu","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05816-6_3"},{"key":"ref49","article-title":"Prioritized experience replay","volume-title":"arXiv:1511.05952","author":"Schaul","year":"2015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1082473.1082537"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2021.3103770"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2789(93)90152-Q"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3417318"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9872163\/09354492.pdf?arnumber=9354492","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:36:51Z","timestamp":1704843411000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9354492\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":56,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3056418","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}