{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T15:56:55Z","timestamp":1781798215368,"version":"3.54.5"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["U20B2060"],"award-info":[{"award-number":["U20B2060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,1]]},"DOI":"10.1109\/tnnls.2021.3089834","type":"journal-article","created":{"date-parts":[[2021,6,28]],"date-time":"2021-06-28T21:16:38Z","timestamp":1624914998000},"page":"90-103","source":"Crossref","is-referenced-by-count":38,"title":["Hierarchical and Stable Multiagent Reinforcement Learning for Cooperative Navigation Control"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0344-4868","authenticated-orcid":false,"given":"Yue","family":"Jin","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5913-1441","authenticated-orcid":false,"given":"Shuangqing","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Louisiana State University, Baton Rouge, LA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9734-6056","authenticated-orcid":false,"given":"Jian","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xudong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2019.2946333"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2007.913992"},{"key":"ref34","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref15","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"66","article-title":"Cooperative multi-agent control using deep reinforcement learning","author":"gupta","year":"2017","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2014.2344291"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2951036"},{"key":"ref31","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":"ref30","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"ref33","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref10","first-page":"2247","article-title":"X*: Anytime multiagent path planning with bounded search","author":"vedder","year":"2019","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref32","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5772\/52768"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2006.878952"},{"key":"ref17","article-title":"Hierarchical deep multiagent reinforcement learning with temporal abstraction","author":"tang","year":"2018","journal-title":"arXiv 1809 09332"},{"key":"ref16","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-006-7035-4"},{"key":"ref18","first-page":"1","article-title":"Federated control with hierarchical multi-agent deep reinforcement learning","author":"kumar","year":"2017","journal-title":"Proc Hierarchical Reinforcement Learn Workshop Neural Inf Process Syst"},{"key":"ref24","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","author":"foerster","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"871","article-title":"Extending Q-learning to general adaptive multi-agent systems","author":"tesauro","year":"2004","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682555"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053534"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref22","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref28","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref27","article-title":"Promoting coordination through policy regularization in multi-agent deep reinforcement learning","author":"roy","year":"2019","journal-title":"arXiv 1908 02269"},{"key":"ref29","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref8","article-title":"Optimal target assignment and path finding for teams of agents","author":"ma","year":"2016","journal-title":"arXiv 1612 05693"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-36279-8_10"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33017643"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2482501"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08338-4_47"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-014-9412-1"},{"key":"ref5","first-page":"4423","article-title":"CoBots: Robust symbiotic autonomous mobile service robots","author":"veloso","year":"2015","journal-title":"Proc Int Joint Conf Artif Intell"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10007736\/09466421.pdf?arnumber=9466421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T19:31:21Z","timestamp":1675107081000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9466421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":37,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2021.3089834","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]}}}