{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:47:03Z","timestamp":1756000023398,"version":"3.37.3"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,17]],"date-time":"2021-10-17T00:00:00Z","timestamp":1634428800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,17]]},"DOI":"10.1109\/smc52423.2021.9658625","type":"proceedings-article","created":{"date-parts":[[2022,1,6]],"date-time":"2022-01-06T20:34:35Z","timestamp":1641501275000},"page":"2967-2972","source":"Crossref","is-referenced-by-count":8,"title":["Multi-Agent Deep Reinforcement Learning using Attentive Graph Neural Architectures for Real-Time Strategy Games"],"prefix":"10.1109","author":[{"given":"Won Joon","family":"Yun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sungwon","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joongheon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"jang","year":"2017","journal-title":"Proceedings of the Fifth International Conference on Learning Representations (ICLR)"},{"key":"ref32","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"arXiv preprint arXiv 1902 11152"},{"key":"ref31","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"arXiv preprint arXiv 1507 06527"},{"key":"ref30","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"arXiv preprint arXiv 1708 04782"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1109\/SMC52423.2021.9658625","article-title":"Multi-agent deep reinforcement learning using attentive graph neural architectures for real-time strategy games","author":"yun","year":"2021"},{"doi-asserted-by":"publisher","key":"ref36","DOI":"10.1145\/203330.203343"},{"key":"ref35","first-page":"1","article-title":"Guided policy search","author":"levine","year":"2013","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref34","DOI":"10.1109\/TII.2019.2895054"},{"doi-asserted-by":"publisher","key":"ref10","DOI":"10.1177\/0278364913495721"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1109\/TSMCC.2007.913919","article-title":"A comprehensive survey of multiagent reinforcement learning","author":"busoniu","year":"2008","journal-title":"IEEE Transactions on Systems Man and Cybernetics"},{"key":"ref12","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"arXiv preprint arXiv 1803 00933"},{"key":"ref13","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2017","journal-title":"arXiv preprint arXiv 1709 02232"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1145\/545056.545078"},{"key":"ref15","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv preprint arXiv 1703 03179"},{"doi-asserted-by":"publisher","key":"ref16","DOI":"10.1109\/GLOBECOM38437.2019.9014151"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref18","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref19","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proceedings of the International Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/TII.2019.2944183"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/JIOT.2020.2988033"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/ICOIN50884.2021.9333895"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/ACCESS.2020.2982647"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TWC.2019.2938755"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1609\/aaai.v34i05.6211"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/JCN.2020.000022"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.24963\/ijcai.2019\/638"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/IJCNN.2019.8852307"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICDCS.2018.00111"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/TRO.2015.2441511"},{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.1109\/TG.2019.2901021"},{"key":"ref20","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proceedings of the Thirty-Seventh International Conference on Machine Learning (ICML)"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/ICUFN.2017.7993784"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1145\/3356464.3357707"},{"doi-asserted-by":"publisher","key":"ref24","DOI":"10.1145\/3292500.3330961"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref26","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems (NIPS)"},{"key":"ref25","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NIPS)"}],"event":{"name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2021,10,17]]},"location":"Melbourne, Australia","end":{"date-parts":[[2021,10,20]]}},"container-title":["2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9658572\/9658575\/09658625.pdf?arnumber=9658625","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:25Z","timestamp":1652201785000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9658625\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,17]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/smc52423.2021.9658625","relation":{},"subject":[],"published":{"date-parts":[[2021,10,17]]}}}