{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:27:51Z","timestamp":1787012871739,"version":"build-2736575974"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61825305"],"award-info":[{"award-number":["61825305"]}],"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":["62003361"],"award-info":[{"award-number":["62003361"]}],"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":["62306325"],"award-info":[{"award-number":["62306325"]}],"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":["U21A20518"],"award-info":[{"award-number":["U21A20518"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcds.2023.3323987","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T14:04:16Z","timestamp":1697465056000},"page":"458-473","source":"Crossref","is-referenced-by-count":7,"title":["GCEN: Multiagent Deep Reinforcement Learning With Grouped Cognitive Feature Representation"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6974-4997","authenticated-orcid":false,"given":"Hao","family":"Gao","sequence":"first","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3238-745X","authenticated-orcid":false,"given":"Xin","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9995-4239","authenticated-orcid":false,"given":"Chao","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4503-643X","authenticated-orcid":false,"given":"Yixing","family":"Lan","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangxing","family":"Yao","sequence":"additional","affiliation":[{"name":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Peng"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811626"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2906260"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3165074"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3100898"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3196925"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"ref11","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"key":"ref12","first-page":"1","article-title":"Dealing with non-stationarity in MARL via trust-region decomposition","volume-title":"Proc. Int. Conf. Learn. Rep. (ICML)","author":"Li"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref14","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. (AAMAS)","author":"Sunehag"},{"key":"ref15","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Rashid"},{"key":"ref16","first-page":"2085","article-title":"QTRAN: learning to factorize with transformation for cooperative multiagent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Son"},{"key":"ref17","first-page":"1","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Rashid"},{"key":"ref18","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Wang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3232390"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.52.1.1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v21i1.13467"},{"key":"ref23","first-page":"7","article-title":"Bayesian reinforcement learning in factored POMDPs","volume-title":"Proc. Auton. Agents Multiagent Syst. (AAMAS)","author":"Katt"},{"key":"ref24","first-page":"193","article-title":"Reinforcement learning of POMDPs using spectral methods","volume-title":"Proc. Annu. Conf. Learn. Theory (COLT)","author":"Azizzadenesheli"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9103-z"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref27","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Conf. Artif. Intell. (AAAI)","author":"Hausknecht"},{"key":"ref28","first-page":"2117","article-title":"Deep variational reinforcement learning for POMDPs","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Igl"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","first-page":"1","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chung"},{"key":"ref31","first-page":"2186","article-title":"The StarCraft multi-agent challenge","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst. (AAMAS)","author":"Samvelyan"},{"key":"ref32","article-title":"Learning to communicate to solve riddles with deep distributed recurrent Q-networks","author":"Foerster","year":"2016","journal-title":"arXiv:1602.02672"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/0022-247X(65)90154-X"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2008.IV.009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-012-9200-2"},{"key":"ref36","first-page":"1729","article-title":"A Bayesian approach for learning and planning in partially observable Markov decision processes","volume":"12","author":"Ross","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9635"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10270"},{"key":"ref39","volume-title":"Playing FPS games with deep reinforcement learning","author":"Lample","year":"2016"},{"key":"ref40","article-title":"On improving deep reinforcement learning for POMDPs","author":"Zhu","year":"2017","journal-title":"arXiv:1704.07978"},{"key":"ref41","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Mahajan"},{"key":"ref42","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Wang"},{"key":"ref43","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Rep. (ICML)","author":"Wang"},{"key":"ref44","first-page":"1989","article-title":"Scaling multi-agent reinforcement learning with selective parameter sharing","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Christianos"},{"key":"ref45","first-page":"1","article-title":"LDSA: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref46","first-page":"1","article-title":"Deep variational information bottleneck","volume-title":"Proc. Int. Conf. Learn. Rep. (ICLR)","author":"Alemi"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982096"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3245124"},{"key":"ref49","first-page":"27862","article-title":"MATE: Benchmarking multi-agent reinforcement learning in distributed target coverage control","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Pan"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10491577\/10286292.pdf?arnumber=10286292","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T15:50:52Z","timestamp":1712677852000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10286292\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":49,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3323987","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}