{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T03:44:12Z","timestamp":1762659852975,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,1]],"date-time":"2021-12-01T00:00:00Z","timestamp":1638316800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 106-2917-I-564-028","MOST 108-2218-E-029-006"],"award-info":[{"award-number":["MOST 106-2917-I-564-028","MOST 108-2218-E-029-006"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["ECCS-1509342","CMMI-1763070"],"award-info":[{"award-number":["ECCS-1509342","CMMI-1763070"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM131403","R01CA226937A1"],"award-info":[{"award-number":["R01GM131403","R01CA226937A1"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2021,12]]},"DOI":"10.1109\/tcyb.2019.2958912","type":"journal-article","created":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T21:01:01Z","timestamp":1578430861000},"page":"5717-5727","source":"Crossref","is-referenced-by-count":14,"title":["Model Learning and Knowledge Sharing for Cooperative Multiagent Systems in Stochastic Environment"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4432-8801","authenticated-orcid":false,"given":"Wei-Cheng","family":"Jiang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9505-7143","authenticated-orcid":false,"given":"Vignesh","family":"Narayanan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6693-3979","authenticated-orcid":false,"given":"Jr-Shin","family":"Li","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2006.281990"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2013.01.008"},{"key":"ref31","first-page":"56","article-title":"Bat $\\mathcal {Q}$\n-learning algorithm","volume":"3","author":"abed-alguni","year":"2017","journal-title":"Jordanian J Comput Inf Technol"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.883264"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2341582"},{"key":"ref36","first-page":"2774","article-title":"Parallel reinforcement learning systems using exploration agents and Dyna-$\\mathcal {Q}$\n algorithm","author":"tateyama","year":"2007","journal-title":"Proc IEEE Annu Conf (SICE)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2004.1521772"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CIRA.2003.1222154"},{"key":"ref10","first-page":"18","article-title":"An empirical comparison of abstraction in models of Markov decision processes","author":"hester","year":"2009","journal-title":"Proc ICML\/UAI\/COLT Workshop Abstraction Reinforcement Learn"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref40"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref12","first-page":"1","article-title":"Model-based reinforcement learning with an approximate, learned model","author":"kuvayev","year":"1996","journal-title":"Proc 9th Yale Workshop Adapt Learn Syst"},{"key":"ref13","first-page":"283","article-title":"Extended Dyna-$\\mathcal {Q}$\n algorithm for path planning of mobile robots","volume":"2","author":"viet","year":"2011","journal-title":"J Meas Sci Instrum"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2847048"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2442233"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2015.2511658"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1329125.1329241"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2517211"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1163\/156855301317198142"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.07.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2014.2311578"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509181"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3477.979961"},{"key":"ref5","first-page":"717","article-title":"Generalized model learning for reinforcement learning in factored domains","volume":"2","author":"hester","year":"2009","journal-title":"Proc 8th Int Conf Auton Agents Multiagent Syst"},{"key":"ref8","article-title":"Learning and using models","author":"hester","year":"2011","journal-title":"Reinforcement Learning State of the Art"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152834"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2558295"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-007-2598-0_49"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref20","first-page":"1","article-title":"$\\mathcal {Q}$\n-learning with experience replay in a dynamic environment","author":"pieters","year":"2016","journal-title":"Proc SSCI"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2544866"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2013.06.016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2542923"},{"key":"ref24","first-page":"4913","article-title":"An advising framework for multiagent reinforcement learning systems","author":"da silva","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2781130"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref43","first-page":"70","article-title":"Decision tree function approximation in reinforcement learning","volume":"2","author":"pyeatt","year":"2001","journal-title":"Proc 3rd Int Symp Adapt Syst Evol Comput Probab Graph Models"},{"key":"ref25","first-page":"1100","article-title":"Simultaneously learning and advising in multiagent reinforcement learning","author":"da silva","year":"2017","journal-title":"Proc 16th Conf Auton Agents MultiAgent Syst"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6221036\/9660196\/8951268-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9660196\/08951268.pdf?arnumber=8951268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:30Z","timestamp":1652194410000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8951268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12]]},"references-count":43,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2019.2958912","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"type":"print","value":"2168-2267"},{"type":"electronic","value":"2168-2275"}],"subject":[],"published":{"date-parts":[[2021,12]]}}}