{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:40:57Z","timestamp":1781757657680,"version":"3.54.5"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62192783"],"award-info":[{"award-number":["62192783"]}],"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":["62106100"],"award-info":[{"award-number":["62106100"]}],"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":["62206133"],"award-info":[{"award-number":["62206133"]}],"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":["92370132"],"award-info":[{"award-number":["92370132"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation 2030 New Generation Artificial Intelligence Major Project","award":["2018AAA0100905"],"award-info":[{"award-number":["2018AAA0100905"]}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20221441"],"award-info":[{"award-number":["BK20221441"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013058","name":"Jiangsu Provincial Key Research and Development Program","doi-asserted-by":"publisher","award":["BE2021028"],"award-info":[{"award-number":["BE2021028"]}],"id":[{"id":"10.13039\/501100013058","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017607","name":"Shenzhen Fundamental Research Program","doi-asserted-by":"publisher","award":["2021Szvup056"],"award-info":[{"award-number":["2021Szvup056"]}],"id":[{"id":"10.13039\/501100017607","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Fund of Guangxi Key Lab of Multi-Source Information Mining and Security","award":["MIMS22-01"],"award-info":[{"award-number":["MIMS22-01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tcyb.2023.3328732","type":"journal-article","created":{"date-parts":[[2023,11,21]],"date-time":"2023-11-21T19:50:34Z","timestamp":1700596234000},"page":"4789-4801","source":"Crossref","is-referenced-by-count":10,"title":["WToE: Learning When to Explore in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8493-1501","authenticated-orcid":false,"given":"Shaokang","family":"Dong","sequence":"first","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4499-7581","authenticated-orcid":false,"given":"Hangyu","family":"Mao","sequence":"additional","affiliation":[{"name":"Smart City Group, SenseTime Research, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangdong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9793-662X","authenticated-orcid":false,"given":"Shengyu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Noah’s Ark Lab, Huawei Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0935-7124","authenticated-orcid":false,"given":"Wenbin","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0422-8235","authenticated-orcid":false,"given":"Jianye","family":"Hao","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-1813","authenticated-orcid":false,"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0025-4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3008612"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2771560"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3236361"},{"key":"ref9","first-page":"4405","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Du"},{"key":"ref10","first-page":"7611","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. 33rd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Mahajan"},{"key":"ref11","first-page":"1","article-title":"Influence-based multi-agent exploration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang"},{"key":"ref12","first-page":"1","article-title":"When should agents explore?","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Pislar"},{"key":"ref13","first-page":"89","article-title":"Near-optimal regret bounds for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Auer"},{"key":"ref14","first-page":"4868","article-title":"Is Q-learning provably efficient?","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Jin"},{"key":"ref15","first-page":"943","article-title":"A Bayesian framework for reinforcement learning","volume-title":"Proc. 17th Int. Conf. Mach. Learn. (ICML)","author":"Strens"},{"key":"ref16","first-page":"1184","article-title":"Optimistic posterior sampling for reinforcement learning: Worst-case regret bounds","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Agrawal"},{"key":"ref17","first-page":"3003","article-title":"(More) efficient reinforcement learning via posterior sampling","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Osband"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2007.08.009"},{"key":"ref19","first-page":"5829","article-title":"Exploration-guided reward shaping for reinforcement learning under sparse rewards","volume-title":"Proc. 36th Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"35","author":"Devidze"},{"key":"ref20","first-page":"1","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. 30th Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Bellemare"},{"key":"ref21","first-page":"1","article-title":"Count-based exploration with neural density models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ostrovski"},{"key":"ref22","first-page":"1","article-title":"Flipping coins to estimate Pseudocounts for exploration in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lobel"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref24","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Burda"},{"key":"ref25","first-page":"1","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Fortunato"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3035783"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3091680"},{"key":"ref28","first-page":"3360","article-title":"EMI: Exploration with mutual information","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","volume":"97","author":"Kim"},{"key":"ref29","first-page":"7120","article-title":"VIREL: A variational inference framework for reinforcement learning","volume-title":"Proc. 33rd Conf. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Fellows"},{"key":"ref30","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Houthooft"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3023127"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3129160"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2958912"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2594500"},{"key":"ref35","first-page":"1","article-title":"Temporally-extended \u03b5-greedy exploration","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Dabney"},{"key":"ref36","first-page":"1","article-title":"Never give up: Learning directed exploration strategies","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Badia"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553508"},{"key":"ref38","article-title":"Reinforcement learning and control as probabilistic inference: Tutorial and review","author":"Levine","year":"2018","journal-title":"arXiv:1805.00909"},{"key":"ref39","first-page":"1","article-title":"Deep reinforcement learning amidst lifelong non-stationarity","volume-title":"Proc. Lifelong Mach. Learn. Workshop Int. Conf. Mach. Learn. (ICML)","author":"Xie"},{"key":"ref40","first-page":"1","article-title":"Probabilistic recursive reasoning for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref42","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","volume-title":"Proc. 19th Nat. Conf. Artif. Intell. (AAAI)","volume":"4","author":"Hansen"},{"key":"ref43","first-page":"1861","article-title":"Soft actor\u2013critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Haarnoja"},{"key":"ref44","first-page":"6379","article-title":"Multi-agent actor\u2013critic for mixed cooperative-competitive environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lowe"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10604457\/10324374.pdf?arnumber=10324374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T18:55:52Z","timestamp":1732906552000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10324374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":45,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2023.3328732","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}