{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T03:18:26Z","timestamp":1784949506524,"version":"3.55.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Council of Finland (former Academy of Finland) 6G Flagship Programme","award":["346208"],"award-info":[{"award-number":["346208"]}]},{"name":"European Commission through the Hexa-X-II","award":["101095759"],"award-info":[{"award-number":["101095759"]}]},{"name":"European Union\u0160s Horizon Europe project CENTRIC","award":["101096379"],"award-info":[{"award-number":["101096379"]}]},{"name":"Open Fellowships of the EPSRC","award":["EP\/W024101\/1"],"award-info":[{"award-number":["EP\/W024101\/1"]}]},{"name":"EPSRC project","award":["EP\/X011852\/1"],"award-info":[{"award-number":["EP\/X011852\/1"]}]},{"name":"Project REASON, a UK Government funded project under the Future Open Networks Research Challenge"},{"name":"Department of Science Innovation and Technology"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Commun. Netw."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tccn.2024.3499357","type":"journal-article","created":{"date-parts":[[2024,11,14]],"date-time":"2024-11-14T18:41:07Z","timestamp":1731609667000},"page":"1913-1926","source":"Crossref","is-referenced-by-count":8,"title":["Conservative and Risk-Aware Offline Multi-Agent Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6322-2036","authenticated-orcid":false,"given":"Eslam","family":"Eldeeb","sequence":"first","affiliation":[{"name":"Centre for Wireless Communications, University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0630-7073","authenticated-orcid":false,"given":"Houssem","family":"Sifaou","sequence":"additional","affiliation":[{"name":"Department of Engineering, King's Communications, Learning and Information Processing Lab, Centre for Intelligent Information Processing Systems, King's College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9898-3209","authenticated-orcid":false,"given":"Osvaldo","family":"Simeone","sequence":"additional","affiliation":[{"name":"Department of Engineering, King's Communications, Learning and Information Processing Lab, Centre for Intelligent Information Processing Systems, King's College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2391-3171","authenticated-orcid":false,"given":"Mohammad","family":"Shehab","sequence":"additional","affiliation":[{"name":"CEMSE Division, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8689-5313","authenticated-orcid":false,"given":"Hirley","family":"Alves","sequence":"additional","affiliation":[{"name":"Centre for Wireless Communications, University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Simulation intelligence: Towards a new generation of scientific methods","author":"Lavin","year":"2021","journal-title":"arXiv:2112.03235"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900292"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2926625"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3073036"},{"key":"ref6","volume-title":"Multi-Agent Reinforcement Learning: Foundations and Modern Approaches","author":"Albrecht","year":"2024"},{"key":"ref7","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/14207.001.0001","volume-title":"Distributional Reinforcement Learning","author":"Bellemare","year":"2023"},{"key":"ref9","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM38437.2019.9013924"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3023861"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3222092"},{"key":"ref13","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kidambi"},{"key":"ref14","first-page":"1","article-title":"Imitation learning by reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ciosek"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref16","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. 34th Conf. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref17","first-page":"1","article-title":"A model-based solution to the offline multi-agent reinforcement learning coordination problem","volume-title":"Proc. 23rd Int. Conf. Auton. Agents Multiagent Syst.","author":"Barde"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3395624"},{"key":"ref19","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref21","first-page":"1096","article-title":"Implicit quantile networks for distributional reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dabney"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21314\/JOR.2000.038"},{"key":"ref23","first-page":"30977","article-title":"Distributional reinforcement learning for risk-sensitive policies","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lim"},{"key":"ref24","first-page":"19235","article-title":"Conservative offline distributional reinforcement learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA230390"},{"key":"ref26","first-page":"17221","article-title":"Plan better amid conservatism: Offline multi-agent reinforcement learning with actor rectification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pan"},{"key":"ref27","first-page":"77290","article-title":"Counterfactual conservative Q learning for offline multi-agent reinforcement learning","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Shao"},{"key":"ref28","first-page":"52413","article-title":"Offline multi-agent reinforcement learning with implicit global-to-local value regularization","volume-title":"Proc. 37th Conf.. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref29","first-page":"10299","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3339514"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322539"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2935201"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933973"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3051163"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3310066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3107520"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9348040"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2959185"},{"key":"ref39","article-title":"Value-decomposition networks for cooperative multi-agent learning","author":"Sunehag","year":"2017","journal-title":"arXiv:1706.05296"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14386"},{"key":"ref41","first-page":"1","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Lowe"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref43","article-title":"Offline RL with no OOD actions: In-sample learning via implicit value regularization","author":"Xu","year":"2023","journal-title":"arXiv:2303.15810"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC\/6GSummit54941.2022.9815722"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2022.3195067"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1561\/9781680833614"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/PIMRC56721.2023.10293964"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"}],"container-title":["IEEE Transactions on Cognitive Communications and Networking"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687307\/11030768\/10753476.pdf?arnumber=10753476","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T04:18:09Z","timestamp":1749701889000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10753476\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":48,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tccn.2024.3499357","relation":{},"ISSN":["2332-7731","2372-2045"],"issn-type":[{"value":"2332-7731","type":"electronic"},{"value":"2372-2045","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}