{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:48:35Z","timestamp":1776181715954,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2020B0101380001"],"award-info":[{"award-number":["2020B0101380001"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62027804"],"award-info":[{"award-number":["62027804"]}],"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":["61825101"],"award-info":[{"award-number":["61825101"]}],"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":["62088102"],"award-info":[{"award-number":["62088102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2023,11,1]]},"DOI":"10.1109\/tkde.2022.3232711","type":"journal-article","created":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T18:35:44Z","timestamp":1672857344000},"page":"11570-11584","source":"Crossref","is-referenced-by-count":33,"title":["MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7818-0767","authenticated-orcid":false,"given":"Liwen","family":"Zhu","sequence":"first","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7427-8764","authenticated-orcid":false,"given":"Peixi","family":"Peng","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3967-2704","authenticated-orcid":false,"given":"Zongqing","family":"Lu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330949"},{"key":"ref57","article-title":"Learning to play with intrinsically-motivated self-aware agents","author":"haber","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220096"},{"key":"ref56","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87479-9_61"},{"key":"ref59","article-title":"Exploration in approximate hyper-state space for meta reinforcement learning","author":"zintgraf","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref58","first-page":"3040","article-title":"Social influence as intrinsic motivation for multi-agent deep reinforcement learning","author":"jaques","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","first-page":"2750","article-title":"# exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref52","first-page":"1471","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070202"},{"key":"ref55","article-title":"Large-scale study of curiosity-driven learning","author":"burda","year":"2018"},{"key":"ref10","first-page":"2133","article-title":"Urban flow pattern mining based on multi-source heterogeneous data fusion and knowledge graph embedding","volume":"35","author":"liu","year":"2023","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref54","first-page":"2721","article-title":"Count-based exploration with neural density models","author":"ostrovski","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref16","first-page":"1","article-title":"Coordinated deep reinforcement learners for traffic light control","author":"van der pol","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref19","first-page":"1","article-title":"Intrinsic motivation for encouraging synergistic behavior","author":"chitnis","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref18","first-page":"5048","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482326"},{"key":"ref50","first-page":"1","article-title":"VariBAD: A very good method for bayes-adaptive deep RL via meta-learning","author":"zintgraf","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357902"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569301"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16147"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/345"},{"key":"ref42","article-title":"AttendLight: Universal attention-based reinforcement learning model for traffic signal control","author":"oroojlooy","year":"2020"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5744"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2901791"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041441"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411859"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3025580"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3127077"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2988008"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3006084"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3130258"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2992565"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2995855"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358079"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2011.6083114"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SASO.2009.23"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/501"},{"key":"ref36","article-title":"Modellight: Model-based meta-reinforcement learning for traffic signal control","author":"huang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1186\/s12544-020-00439-1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25808-9_4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.trb.2019.01.012"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2009.04.005"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.01.007"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2013.2255286"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6243-9_2"},{"key":"ref1","article-title":"Traffic signal timing manual","author":"koonce","year":"2008"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357900"},{"key":"ref38","article-title":"Diagnosing reinforcement learning for traffic signal control","author":"zheng","year":"2019"},{"key":"ref71","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1561\/2200000049"},{"key":"ref73","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref72","author":"roess","year":"2004","journal-title":"Traffic Engineering"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.07.029"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2948953"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-5113-5_3"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.108206"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2873790"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143932"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3314139"},{"key":"ref64","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","author":"gupta","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref63","first-page":"12600","article-title":"Metacure: Meta reinforcement learning with empowerment-driven exploration","author":"zhang","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref22","first-page":"122","article-title":"Adaptive traffic signal control using fuzzy logic","author":"chiu","year":"1992","journal-title":"Proc IEEE Intell Veh Symp"},{"key":"ref66","article-title":"Rl $^{2}$2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016"},{"key":"ref21","article-title":"Traffic signal settings","author":"webster","year":"1958"},{"key":"ref65","article-title":"Auto-encoding variational bayes","author":"kingma","year":"2013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MITS.2016.2605318"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/0361198120919746"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.trc.2016.08.001"},{"key":"ref60","article-title":"Offline meta learning of exploration","author":"dorfman","year":"2020"},{"key":"ref62","article-title":"Learning adaptive exploration strategies in dynamic environments through informed policy regularization","author":"kamienny","year":"2020"},{"key":"ref61","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10273671\/10006753.pdf?arnumber=10006753","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T18:26:35Z","timestamp":1698085595000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10006753\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":77,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2022.3232711","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,1]]}}}