{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:22:42Z","timestamp":1740169362322,"version":"3.37.3"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","award":["2022R1A2C2004869"],"award-info":[{"award-number":["2022R1A2C2004869"]}],"id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3439354","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T18:18:37Z","timestamp":1722968317000},"page":"108504-108514","source":"Crossref","is-referenced-by-count":0,"title":["Farthest Agent Selection With Episode-Wise Observations for Real-Time Multi-Agent Reinforcement Learning Applications"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1113-9019","authenticated-orcid":false,"given":"Hyunsoo","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5559-9749","authenticated-orcid":false,"given":"Gyu Seon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7027-1920","authenticated-orcid":false,"given":"Minseok","family":"Choi","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Kyung Hee University, Yongin, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4670-6817","authenticated-orcid":false,"given":"Hankyul","family":"Baek","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6556-9746","authenticated-orcid":false,"given":"Soohyun","family":"Park","sequence":"additional","affiliation":[{"name":"Division of Computer Science, Sookmyung Women’s University, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS57875.2023.00014"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3335597"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796717"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"ref6","first-page":"4292","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"80","author":"Rashid"},{"key":"ref7","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Son"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2944183"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215774"},{"issue":"1","key":"ref11","first-page":"1","article-title":"Heterogeneousagent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","first-page":"705","article-title":"Taming decentralized POMDPs: Towards efficient policy computation for multiagent settings","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Nair"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557078"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3143175"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tvt.2024.3369089"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2024.3368367"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref18","first-page":"27840","article-title":"Attention-based recurrence for multi-agent reinforcement learning under stochastic partial observability","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Phan"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3053633"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn55064.2022.9892913"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref22","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","volume":"29","author":"Sukhbaatar"},{"key":"ref23","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTCC59206.2023.10308458"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3283235"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279436"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2021.01.005"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7886"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00563"},{"key":"ref30","first-page":"5105","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Qi"},{"key":"ref31","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. ACM Int. Conf. Auto. Agents MultiAgent Syst. (AAMAS)","author":"Sunehag"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref33","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume":"abs\/1902.0404","author":"Samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SMC52423.2021.9658625"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.17148\/IARJSET.2015.2305"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.21236\/ada333248"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10623680.pdf?arnumber=10623680","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T05:16:05Z","timestamp":1723526165000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10623680\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3439354","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}