{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T06:52:09Z","timestamp":1762325529005,"version":"3.37.3"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Science and Technology Council, Taiwan","award":["MOST 110-2221-E-128-001"],"award-info":[{"award-number":["MOST 110-2221-E-128-001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Systems Journal"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/jsyst.2023.3240768","type":"journal-article","created":{"date-parts":[[2023,2,16]],"date-time":"2023-02-16T21:05:03Z","timestamp":1676581503000},"page":"3783-3793","source":"Crossref","is-referenced-by-count":1,"title":["An Attentive Consensus Platform for Collaborative Reinforcement Learning Agents"],"prefix":"10.1109","volume":"17","author":[{"given":"Maxwell","family":"Hwang","sequence":"first","affiliation":[{"name":"School of Microelectronics, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5762-4557","authenticated-orcid":false,"given":"Jin-Ling","family":"Lin","sequence":"additional","affiliation":[{"name":"Information Management, Shih Hsin University, Taipei, Taiwan"}]},{"given":"Shao-Wei","family":"Kao","sequence":"additional","affiliation":[{"name":"a renowned high-tech electronics company, Hsinchu"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2016.7565951"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.14198\/JoPha.2008.2.1.02"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2014.2299559"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-005-2631-2"},{"key":"ref5","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"article-title":"A survey of RL algorithms for dynamically varying environments","year":"2020","author":"Padakandla","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.32604\/jai.2020.09789"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-71682-4_5"},{"key":"ref12","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lowe","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref14","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref16","first-page":"4295","article-title":"QMIX: Monotonic value function factorization for deep multi-agent reinforcement learning","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref17","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Sunehag","year":"2018"},{"article-title":"Multi-focus attention network for efficient deep reinforcement learning","year":"2017","author":"Choi","key":"ref18"},{"article-title":"Learning attentional communication for multi-agent cooperation","year":"2018","author":"Jiang","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14435-6_7"},{"key":"ref21","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Xu","year":"2015"},{"key":"ref22","first-page":"1412","article-title":"Effective approaches to attention-based neural machine translation","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Luong","year":"2015"},{"key":"ref23","first-page":"1","article-title":"Attention in natural language processing","volume-title":"Proc. IEEE Trans. Neural Netw. Learn. Syst.","author":"Galassi","year":"2020"},{"issue":"4","key":"ref24","article-title":"An attentive survey of attention models","volume":"37","author":"Chaudhari","year":"2020","journal-title":"J. ACM"},{"key":"ref25","first-page":"1243","article-title":"Learning to combine foveal glimpses with a third-order Boltzmann machine","author":"Larochelle","year":"2010","journal-title":"NIPS"},{"key":"ref26","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Mnih","year":"2014"},{"volume-title":"RL: An Introduction","year":"2015","author":"Sutton","key":"ref27"},{"article-title":"A survey of RL techniques: Strategies, recent development, and future directions","year":"2020","author":"Kumar Mondal","key":"ref28"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"ref30","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"275","DOI":"10.1016\/j.neucom.2021.06.049","article-title":"Multi-agent reinforcement learning by the actor-critic model with an attention interface","volume":"471","author":"Zhang","year":"2021","journal-title":"Neurocomputing"},{"key":"ref32","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"year":"2021","key":"ref33","article-title":"A large-scale benchmark and challenges for object detection in aerial images"}],"container-title":["IEEE Systems Journal"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4267003\/10235272\/10043783.pdf?arnumber=10043783","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T19:47:21Z","timestamp":1709408841000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10043783\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jsyst.2023.3240768","relation":{},"ISSN":["1932-8184","1937-9234","2373-7816"],"issn-type":[{"type":"print","value":"1932-8184"},{"type":"electronic","value":"1937-9234"},{"type":"electronic","value":"2373-7816"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}