{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T22:02:24Z","timestamp":1770847344300,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Institute of Information and communications Technology Planning and Evaluation","award":["RS-2021-II212068-AIHub\/10%"],"award-info":[{"award-number":["RS-2021-II212068-AIHub\/10%"]}]},{"name":"Institute of Information and communications Technology Planning and Evaluation","award":["RS-2021-II211343-GSAI\/10%"],"award-info":[{"award-number":["RS-2021-II211343-GSAI\/10%"]}]},{"name":"Institute of Information and communications Technology Planning and Evaluation","award":["RS-2022-II220951-LBA\/10%"],"award-info":[{"award-number":["RS-2022-II220951-LBA\/10%"]}]},{"name":"Institute of Information and communications Technology Planning and Evaluation","award":["RS-2022-II220953-PICA\/10%"],"award-info":[{"award-number":["RS-2022-II220953-PICA\/10%"]}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["RS-2024-00353991-SPARC\/10%"],"award-info":[{"award-number":["RS-2024-00353991-SPARC\/10%"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["RS-2023-00274280-HEI\/10%"],"award-info":[{"award-number":["RS-2023-00274280-HEI\/10%"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"crossref","award":["RS-2024-00358416-AutoRL\/10%"],"award-info":[{"award-number":["RS-2024-00358416-AutoRL\/10%"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003662","name":"Korea Evaluation Institute of Industrial Technology","doi-asserted-by":"crossref","award":["RS-2024-00423940\/10%"],"award-info":[{"award-number":["RS-2024-00423940\/10%"]}],"id":[{"id":"10.13039\/501100003662","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ministry of Trade Industry & Resources (MOTIR), grant funded by the Korean government","award":["RS-2025-25453780\/10%"],"award-info":[{"award-number":["RS-2025-25453780\/10%"]}]},{"name":"Ministry of Trade Industry & Resources (MOTIR), grant funded by the Korean government","award":["RS-2025-25460896\/10%"],"award-info":[{"award-number":["RS-2025-25460896\/10%"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3660261","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T20:56:06Z","timestamp":1770152166000},"page":"19363-19373","source":"Crossref","is-referenced-by-count":0,"title":["Communicating Unexpectedness for Out-of-Distribution Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6681-1031","authenticated-orcid":false,"given":"Min Whoo","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4003-7812","authenticated-orcid":false,"given":"Yunsu","family":"Lee","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kibeom","family":"Kim","sequence":"additional","affiliation":[{"name":"Hyundai Motor Company, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4158-0529","authenticated-orcid":false,"given":"Soo Wung","family":"Shin","sequence":"additional","affiliation":[{"name":"Jinhakapply Corporation, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3926-8613","authenticated-orcid":false,"given":"Jun Ki","family":"Lee","sequence":"additional","affiliation":[{"name":"AI Institute (AIIS), Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9601-3863","authenticated-orcid":false,"given":"Minsu","family":"Lee","sequence":"additional","affiliation":[{"name":"School of AI Convergence, Sungshin Women’s University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9890-0389","authenticated-orcid":false,"given":"Byoung-Tak","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jai.2024.02.003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.09.044"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3268082"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3165074"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-023-09633-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.65109\/JSRC7365"},{"key":"ref10","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref11","first-page":"11609","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3339656"},{"key":"ref13","article-title":"Dealing with non-stationarity in multi-agent deep reinforcement learning","author":"Papoudakis","year":"2019","journal-title":"arXiv:1906.04737"},{"key":"ref14","article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","author":"Hernandez-Leal","year":"2017","journal-title":"arXiv:1707.09183"},{"key":"ref15","first-page":"6860","article-title":"Coach-player multi-agent reinforcement learning for dynamic team composition","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu"},{"key":"ref16","first-page":"5711","article-title":"Self-organized group for cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref19","first-page":"10488","article-title":"A fine-grained analysis on distribution shift","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wiles"},{"key":"ref20","article-title":"Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track (Round 1)","author":"Papoudakis"},{"key":"ref21","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaques"},{"key":"ref22","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref23","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14174"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref26","first-page":"34961","article-title":"Revisiting data augmentation in deep reinforcement learning","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref27","first-page":"22595","article-title":"Sample complexity of distributionally robust off-dynamics reinforcement learning with online interaction","volume-title":"Proc. Forty-second Int. Conf. Mach. Learn.","author":"Yiting"},{"key":"ref28","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref30","first-page":"13111","article-title":"Biases for emergent communication in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Eccles"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.65109\/edcb3795"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.65109\/yyap1276"},{"key":"ref33","article-title":"Promoting resilience in multi-agent reinforcement learning via confusion-based communication","author":"Abu","year":"2021","journal-title":"arXiv:2111.06614"},{"key":"ref34","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref35","first-page":"103","article-title":"On the properties of neural machine translation: Encoder\u2013decoder approaches","volume-title":"Proc. SSST-8, 8th Workshop Syntax, Semantics Struct. Stat. Transl.","author":"Cho"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11370756.pdf?arnumber=11370756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T20:56:44Z","timestamp":1770843404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11370756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3660261","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}