{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:59:24Z","timestamp":1777129164848,"version":"3.51.4"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003696","name":"Electronics and Telecommunications Research Institute (ETRI) funded by the Korean Government","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003696","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Core Technology Research for Self-Improving Integrated Artificial Intelligence System","award":["22ZS1100"],"award-info":[{"award-number":["22ZS1100"]}]},{"name":"Exploratory Research for Human-Agent Collaboration in Multi-Agent Games","award":["19YE1410"],"award-info":[{"award-number":["19YE1410"]}]},{"DOI":"10.13039\/100000181","name":"AFOSR","doi-asserted-by":"publisher","award":["FA2386-19-1-4020"],"award-info":[{"award-number":["FA2386-19-1-4020"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3198981","type":"journal-article","created":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T19:51:16Z","timestamp":1660593076000},"page":"87254-87265","source":"Crossref","is-referenced-by-count":14,"title":["CuMARL: Curiosity-Based Learning in Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-6584","authenticated-orcid":false,"given":"Devarani Devi","family":"Ningombam","sequence":"first","affiliation":[{"name":"Department of Informatics, School of Computer Science, University of Petroleum and Energy Studies (UPES), Dehradun, Uttarakhand, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0857-5565","authenticated-orcid":false,"given":"Byunghyun","family":"Yoo","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun Woo","family":"Kim","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8216-4812","authenticated-orcid":false,"given":"Hwa Jeon","family":"Song","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4986-9546","authenticated-orcid":false,"given":"Sungwon","family":"Yi","sequence":"additional","affiliation":[{"name":"Electronics and Telecommunications Research Institute (ETRI), Daejeon, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"3341","article-title":"Collaborative evolutionary reinforcement learning","author":"khadka","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (PMLR)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3055511"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/1131260"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.49.1.1"},{"key":"ref15","first-page":"1","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","author":"zheng","year":"2021","journal-title":"Proc 35th Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref16","first-page":"2186","article-title":"The starcraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"Proc 18th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref17","first-page":"1","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","author":"wang","year":"2021","journal-title":"Proc ICLR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAIRO47923.2019.00035"},{"key":"ref4","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 (ICML)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/app10196925"},{"key":"ref3","first-page":"8","article-title":"LIIR: Learning individual intrinsic reward in multi-agent reinforcement learning","author":"du","year":"2019","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3012204"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3113350"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2015.05.002"},{"key":"ref29","first-page":"1146","article-title":"Stabilising experience replay for deep multi-agent reinforcement learning","volume":"70","author":"foerster","year":"2018","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref8","first-page":"280","article-title":"Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2017","journal-title":"Proc 31st Conf Neural Inf Process Syst (NIPS)"},{"key":"ref7","first-page":"1479","article-title":"Unifying count-based exploration and intrinsic motivation","author":"bellemare","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst (NIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2010.2051031"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref1","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05845-8"},{"key":"ref22","first-page":"80","article-title":"Coordinated exploration in concurrent reinforcement learning","author":"dimakopoulou","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref21","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","author":"son","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref24","first-page":"1","article-title":"Inequity aversion improves cooperation in intertemporal social dilemmas","author":"hughes","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst (NeurIPS)"},{"key":"ref23","article-title":"Scalable coordinated exploration in concurrent reinforcement learning","author":"dimakopoulou","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/589"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5968"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09857920.pdf?arnumber=9857920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,19]],"date-time":"2022-09-19T20:23:05Z","timestamp":1663618985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9857920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3198981","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}