{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T16:05:35Z","timestamp":1781971535357,"version":"3.54.5"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China International Technology Cooperation Project","award":["2021YFE014400"],"award-info":[{"award-number":["2021YFE014400"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372243"],"award-info":[{"award-number":["62372243"]}],"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":["42175194"],"award-info":[{"award-number":["42175194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Provincial Graduate Research and Practical Innovation Program","award":["KYCX23_1358"],"award-info":[{"award-number":["KYCX23_1358"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tetci.2023.3309738","type":"journal-article","created":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T19:16:02Z","timestamp":1694459762000},"page":"533-547","source":"Crossref","is-referenced-by-count":13,"title":["Hierarchical Coordination Multi-Agent Reinforcement Learning With Spatio-Temporal Abstraction"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2320-1692","authenticated-orcid":false,"given":"Tinghuai","family":"Ma","sequence":"first","affiliation":[{"name":"School of Software, Nanjing University of Information Science & Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2712-9088","authenticated-orcid":false,"given":"Kexing","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Information Science & Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-1827","authenticated-orcid":false,"given":"Huan","family":"Rong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Nanjing University of Information Science & Technology, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-4745","authenticated-orcid":false,"given":"Yurong","family":"Qian","sequence":"additional","affiliation":[{"name":"Xinjiang University, Urumqi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0805-1721","authenticated-orcid":false,"given":"Najla","family":"Al-Nabhan","sequence":"additional","affiliation":[{"name":"Department of Computer Science, King Saud University, Riyadh, Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2022.103560"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3141105"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3177027"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00433-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2022.110491"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3164696"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3155734"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2022.3200138"},{"key":"ref9","first-page":"15007","article-title":"On improving model-free algorithms for decentralized multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao","year":"2022"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569938"},{"key":"ref11","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2022.3207429"},{"key":"ref13","first-page":"3303","article-title":"Data-efficient hierarchical reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Nachum","year":"2018"},{"key":"ref14","first-page":"1409","article-title":"Hierarchical reinforcement learning with advantage-based auxiliary rewards","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2019"},{"key":"ref15","first-page":"57","article-title":"Feudal multi-agent hierarchies for cooperative reinforcement learning","volume-title":"Proc. Conf. Reinforcement Decis.","author":"Ahilan","year":"2019"},{"key":"ref16","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahajan","year":"2019"},{"key":"ref17","first-page":"26","article-title":"Rode: Learning roles to decompose multi-agent tasks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref18","first-page":"2145","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Foerster","year":"2016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref20","first-page":"1","article-title":"Communication in multi-agent reinforcement learning: Intention sharing","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2020"},{"key":"ref21","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3140375"},{"key":"ref23","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2016"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"ref25","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.","author":"Sunehag","year":"2018"},{"key":"ref26","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref27","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"key":"ref28","article-title":"Graph convolutional value decomposition in multi-agent reinforcement learning","author":"Naderializadeh","year":"2020"},{"key":"ref29","first-page":"9876","article-title":"ROMA: Multi-agent reinforcement learning with emergent roles","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref30","first-page":"1","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2021"},{"key":"ref31","first-page":"4403","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Du","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-5164-9_5"},{"key":"ref33","first-page":"1630","article-title":"Multiagent Q-learning with sub-team coordination","volume-title":"Proc. 21st Int. Conf. Auton. Agents Multiagent Syst.","author":"Huang","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3390\/make4010009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.apm.2022.01.036"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3210998"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3186180"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2022.3209655"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3136642"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10412693\/10246843.pdf?arnumber=10246843","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T18:55:23Z","timestamp":1732647323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10246843\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":39,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2023.3309738","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}