{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T21:36:56Z","timestamp":1781905016713,"version":"3.54.5"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0107200"],"award-info":[{"award-number":["2020AAA0107200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921006"],"award-info":[{"award-number":["61921006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876119"],"award-info":[{"award-number":["61876119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276126"],"award-info":[{"award-number":["62276126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Jiangsu","award":["BK20221442"],"award-info":[{"award-number":["BK20221442"]}]},{"name":"Natural Science Foundation of Jiangsu","award":["BK20243039"],"award-info":[{"award-number":["BK20243039"]}]},{"name":"Natural Science Foundation of Jiangsu","award":["BK2024119"],"award-info":[{"award-number":["BK2024119"]}]},{"name":"Program B for Outstanding Ph.D. Candidate of Nanjing University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tnnls.2024.3420791","type":"journal-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T18:04:47Z","timestamp":1726509887000},"page":"9044-9056","source":"Crossref","is-referenced-by-count":7,"title":["Efficient Communication via Self-Supervised Information Aggregation for Online and Offline Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5198-9141","authenticated-orcid":false,"given":"Cong","family":"Guan","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8164-3410","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7803-0766","authenticated-orcid":false,"given":"Lei","family":"Yuan","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9238-4747","authenticated-orcid":false,"given":"Zongzhang","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-5447","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology and the School of Artificial Intelligence, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09938-y"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref3","article-title":"A survey of progress on cooperative multiagent reinforcement learning in open environment","author":"Yuan","year":"2023","journal-title":"arXiv:2312.01058"},{"key":"ref4","first-page":"1","article-title":"Multiagent reinforcement learning is a sequence modeling problem","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"issue":"2","key":"ref5","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI","volume":"29","author":"Hausknecht"},{"key":"ref6","first-page":"1","article-title":"Learning nearly decomposable value functions via communication minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref7","first-page":"22069","article-title":"Learning individually inferred communication for multiagent cooperation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ding"},{"key":"ref8","article-title":"A survey of multiagent reinforcement learning with communication","author":"Zhu","year":"2022","journal-title":"arXiv:2203.08975"},{"key":"ref9","first-page":"17271","article-title":"Succinct and robust multiagent communication with temporal message control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref10","first-page":"1538","article-title":"TarMAC: Targeted multiagent communication","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Das"},{"key":"ref11","first-page":"964","article-title":"Multiagent graph-attention communication and teaming","volume-title":"Proc. 20th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Niu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5957"},{"key":"ref13","first-page":"1","article-title":"Data-efficient reinforcement learning with self-predictive representations","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schwarzer"},{"key":"ref14","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref15","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019","journal-title":"arXiv:1910.01708"},{"key":"ref16","first-page":"10299","article-title":"Believe what you see: Implicit constraint approach for offline multiagent reinforcement learning","volume-title":"Proc. Adv. neural Inf. Process. Syst.","author":"Yang"},{"key":"ref17","first-page":"17221","article-title":"Plan better AMID conservatism: Offline multiagent reinforcement learning with actor rectification","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pan"},{"key":"ref18","article-title":"Off-the-grid MARL: A framework for dataset generation with baselines for cooperative offline multiagent reinforcement learning","author":"Claude","year":"2023","journal-title":"arXiv:2302.00521"},{"key":"ref19","article-title":"Benchmarking multiagent deep reinforcement learning algorithms in cooperative tasks","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Papoudakis"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref21","article-title":"A model-based solution to the offline multiagent reinforcement learning coordination problem","author":"Barde","year":"2023","journal-title":"arXiv:2305.17198"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref23","first-page":"2085","article-title":"Value-decomposition networks for cooperative multiagent learning based on team reward","volume-title":"Proc. 17th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Sunehag"},{"key":"ref24","first-page":"4295","article-title":"QMix: Monotonic value function factorisation for deep multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid"},{"key":"ref25","first-page":"1","article-title":"QPLEX: Duplex dueling multiagent Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref26","first-page":"1156","article-title":"Context-aware communication for multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Li"},{"key":"ref27","first-page":"1","article-title":"Learning multiagent communication with contrastive learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lo"},{"key":"ref28","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref29","article-title":"Regularized behavior value estimation","author":"Gulcehre","year":"2021","journal-title":"arXiv:2103.09575"},{"key":"ref30","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref31","first-page":"1","article-title":"Empirical study of off-policy policy evaluation for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Voloshin"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref33","first-page":"12491","article-title":"FOP: Factorizing optimal joint policy of maximum-entropy multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref34","article-title":"Trust region policy optimisation in multiagent reinforcement learning","author":"Grudzien Kuba","year":"2021","journal-title":"arXiv:2109.11251"},{"key":"ref35","first-page":"29142","article-title":"Towards understanding cooperative multiagent Q-learning with value factorization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref36","first-page":"2137","article-title":"Learning to communicate with deep multiagent reinforcement learning","volume-title":"Proc. Conf. Adv. Neural Inf. Process. Syst.","author":"Foerster"},{"key":"ref37","first-page":"2244","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref38","first-page":"3230","article-title":"Efficient communication in multiagent reinforcement learning via variance based control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309608"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3230701"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3049345"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3233\/faia230390"},{"key":"ref45","article-title":"Offline pre-trained multiagent decision transformer: One big sequence model conquers all starcraftii tasks","author":"Meng","year":"2021","journal-title":"arXiv:2112.02845"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i10.26379"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/10982361\/10680461.pdf?arnumber=10680461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T17:57:09Z","timestamp":1746467829000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10680461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":46,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3420791","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}