{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,20]],"date-time":"2025-03-20T04:04:34Z","timestamp":1742443474790,"version":"3.40.1"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Agency for Defense Development by the Korean Goverment","award":["915054103"],"award-info":[{"award-number":["915054103"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tg.2024.3399167","type":"journal-article","created":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:33:11Z","timestamp":1715362391000},"page":"138-147","source":"Crossref","is-referenced-by-count":0,"title":["A Hetero-Relation Transformer Network for Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-5421-594X","authenticated-orcid":false,"given":"Junho","family":"Park","sequence":"first","affiliation":[{"name":"Defense AI Center, Agency for Defense Development, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3241-0851","authenticated-orcid":false,"given":"Sukmin","family":"Yoon","sequence":"additional","affiliation":[{"name":"Defense AI Center, Agency for Defense Development, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3017-6095","authenticated-orcid":false,"given":"Yong-Duk","family":"Kim","sequence":"additional","affiliation":[{"name":"Defense AI Center, Agency for Defense Development, Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2834566"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3095264"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2013.6631119"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3075065"},{"issue":"1","key":"ref5","first-page":"7234","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3232390"},{"key":"ref7","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref8","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp. Ser.","author":"Hausknecht","year":"2015"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref10","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref12","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Velikovi","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"ref15","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref17","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref18","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 MultiAgent Syst.","author":"Sunehag","year":"2018"},{"key":"ref19","article-title":"Hypernetworks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ha","year":"2016"},{"key":"ref20","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"33","author":"Rashid","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref21","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang","year":"2016"},{"key":"ref22","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26390"},{"key":"ref24","article-title":"Automatic grouping for efficient cooperative multi-agent reinforcement learning","volume":"36","author":"Zang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref25","article-title":"Graph convolutional reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Jiang","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215774"},{"key":"ref28","first-page":"1485","article-title":"Heterogeneous multi-robot reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Bettini","year":"2023"},{"key":"ref29","article-title":"UPDeT: Universal multi-agent RL via policy decoupling with transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref30","first-page":"1679","article-title":"TransfQMix: Transformers for leveraging the graph structure of multi-agent reinforcement learning problems","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Gallici","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14778\/3402707.3402736"},{"article-title":"Bidirectional LSTM-CRF models for sequence tagging","year":"2015","author":"Huang","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467350"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref36","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10931171\/10528877.pdf?arnumber=10528877","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T04:59:29Z","timestamp":1742360369000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10528877\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2024.3399167","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}