{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T16:09:23Z","timestamp":1781194163969,"version":"3.54.1"},"reference-count":18,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T00:00:00Z","timestamp":1753747200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["ICT Express"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.icte.2025.07.010","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T03:45:58Z","timestamp":1755747958000},"page":"301-305","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"title":["Learning graph based individual intrinsic reward for multi-agent reinforcement learning"],"prefix":"10.1016","volume":"12","author":[{"given":"Seokhun","family":"Ju","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungyub","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taehyun","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6804-980X","authenticated-orcid":false,"given":"Jungwoo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taeyoung","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minkyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinho","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.icte.2025.07.010_b1","volume":"vol. 17","author":"Sutton","year":"1999"},{"issue":"7587","key":"10.1016\/j.icte.2025.07.010_b2","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"},{"issue":"7782","key":"10.1016\/j.icte.2025.07.010_b3","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"issue":"3","key":"10.1016\/j.icte.2025.07.010_b4","doi-asserted-by":"crossref","first-page":"191","DOI":"10.5626\/JOK.2024.51.3.191","article-title":"A reinforcement learning based adaptive container scheduling back-off scheme for reducing cold starts in faas platforms","volume":"51","author":"Kang","year":"2024","journal-title":"J. KIISE"},{"issue":"8","key":"10.1016\/j.icte.2025.07.010_b5","doi-asserted-by":"crossref","first-page":"871","DOI":"10.5626\/JOK.2021.48.8.871","article-title":"Reinforcement learning-based traffic signal control under real-world constraints","volume":"48","author":"Pi","year":"2021","journal-title":"J. KIISE"},{"key":"10.1016\/j.icte.2025.07.010_b6","series-title":"Conference on Robot Learning","article-title":"i-sim2real: Reinforcement learning of robotic policies in tight human\u2013robot interaction loops","author":"Abeyruwan","year":"2023"},{"key":"10.1016\/j.icte.2025.07.010_b7","article-title":"Counterfactual multi-agent policy gradients","volume":"vol. 32","author":"Foerster","year":"2018"},{"key":"10.1016\/j.icte.2025.07.010_b8","doi-asserted-by":"crossref","unstructured":"P. Sunehag, et al., Value-decomposition networks for cooperative multi-agent learning based on team reward, in: Proceedings of the 17th International Conference on Autonomous Agents and Multi Agent Systems, 2018.","DOI":"10.65109\/JSRC7365"},{"issue":"178","key":"10.1016\/j.icte.2025.07.010_b9","first-page":"1","article-title":"Monotonic value function factorisation for deep multi-agent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"10.1016\/j.icte.2025.07.010_b10","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1287\/moor.27.4.819.297","article-title":"The complexity of decentralized control of markov decision processes","volume":"27","author":"Bernstein","year":"2002","journal-title":"Math. Oper. Res."},{"key":"10.1016\/j.icte.2025.07.010_b11","article-title":"Liir: Learning individual intrinsic reward in multi-agent reinforcement learning","volume":"vol. 32","author":"Du","year":"2019"},{"key":"10.1016\/j.icte.2025.07.010_b12","unstructured":"K. Lee, et al., Pebble: Feedback-efficient interactive reinforcement learning via relabeling experience and unsupervised pre-training, in: ICML."},{"key":"10.1016\/j.icte.2025.07.010_b13","article-title":"Attention is all you need","volume":"vol. 30","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.icte.2025.07.010_b14","unstructured":"C. Kim, J. Park, J. Shin, H. Lee, P. Abbeel, K. Lee, Preference transformer: Modeling human preferences using transformers for rl, in: 11th International Conference on Learning Representations, ICLR 2023, 2023."},{"key":"10.1016\/j.icte.2025.07.010_b15","first-page":"729","article-title":"A new model for learning in graph domains","volume":"vol. 2","author":"Gori","year":"2005"},{"key":"10.1016\/j.icte.2025.07.010_b16","unstructured":"P. Velic\u0306kovic\u0306, et al., Graph attention networks, in: International Conference on Learning Representations, 2018."},{"issue":"7540","key":"10.1016\/j.icte.2025.07.010_b17","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"10.1016\/j.icte.2025.07.010_b18","unstructured":"M. Samvelyan, et al. The starcraft multi-agent challenge, arXiv preprint arXiv:1902.04043."}],"container-title":["ICT Express"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2405959525001109?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S2405959525001109?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T21:44:33Z","timestamp":1773351873000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S2405959525001109"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":18,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["S2405959525001109"],"URL":"https:\/\/doi.org\/10.1016\/j.icte.2025.07.010","relation":{},"ISSN":["2405-9595"],"issn-type":[{"value":"2405-9595","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Learning graph based individual intrinsic reward for multi-agent reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"ICT Express","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.icte.2025.07.010","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Authors. Published by Elsevier B.V. on behalf of The Korean Institute of Communications and Information Sciences.","name":"copyright","label":"Copyright"}]}}