{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T01:52:14Z","timestamp":1768009934664,"version":"3.49.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/OAPA.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772387"],"award-info":[{"award-number":["61772387"]}],"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":["61372068"],"award-info":[{"award-number":["61372068"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Research Foundation of Ministry of Education and China Mobile","award":["MCM20170202"],"award-info":[{"award-number":["MCM20170202"]}]},{"name":"ISN State Key Laboratory"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2018]]},"DOI":"10.1109\/access.2018.2868476","type":"journal-article","created":{"date-parts":[[2018,9,4]],"date-time":"2018-09-04T18:19:56Z","timestamp":1536085196000},"page":"49721-49731","source":"Crossref","is-referenced-by-count":11,"title":["Monopolistic Models for Resource Allocation: A Probabilistic Reinforcement Learning Approach"],"prefix":"10.1109","volume":"6","author":[{"given":"Yue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8096-3370","authenticated-orcid":false,"given":"Bin","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Su","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojiang","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohsen","family":"Guizani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2018.2809722"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref31","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2017.1600117"},{"key":"ref36","first-page":"453","article-title":"Reinforcement learning","volume":"12","author":"marco","year":"2012","journal-title":"Adaptation Learning and Optimization"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11277-012-0611-9"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1016\/S1574-0021(05)02016-2","article-title":"Agent-based computational economics: A constructive approach to economic theory","volume":"2","author":"leigh","year":"2006","journal-title":"Handbook of Computational Economics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.11.015"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2014.2298837"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT.2014.6803166"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2012.07.010"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2416657"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2016.7553030"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2010.04.004"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2017.02.013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1049\/iet-com.2013.0817"},{"key":"ref19","first-page":"1039","article-title":"Nash Q-learning for general-sum stochastic games","volume":"4","author":"hu","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/VETECF.2010.5594301"},{"key":"ref4","first-page":"1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1904","DOI":"10.1109\/TVT.2008.2002917","article-title":"Learning to compete for resources in wireless stochastic games","volume":"58","author":"fu","year":"2009","journal-title":"IEEE Trans Veh Technol"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2006.05.001"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2017.01.026"},{"key":"ref29","first-page":"1","article-title":"A survey of dynamic spectrum allocation based on reinforcement learning algorithms in cognitive radio networks","volume":"2","author":"wang","year":"2018","journal-title":"Artif Intell Rev"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2006.888977"},{"key":"ref8","author":"mankiw","year":"2014","journal-title":"Principles of Macroeconomics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1561\/1300000001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-68832-9_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2319555"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2004.839380"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2009.080884"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-016-1350-8"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2690866"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2009.4907555"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600444CM"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"7280","DOI":"10.1073\/pnas.082080899","article-title":"Agent-based modeling: Methods and techniques for simulating human systems","volume":"99","author":"eric","year":"2002","journal-title":"Proc Nat Acad Sci USA"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8274985\/08454441.pdf?arnumber=8454441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:15:36Z","timestamp":1642004136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8454441\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2018.2868476","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}