{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T10:05:29Z","timestamp":1775815529151,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T00:00:00Z","timestamp":1607472000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T00:00:00Z","timestamp":1607472000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,12,9]],"date-time":"2020-12-09T00:00:00Z","timestamp":1607472000000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,12,9]]},"DOI":"10.1109\/isspit51521.2020.9408808","type":"proceedings-article","created":{"date-parts":[[2021,4,23]],"date-time":"2021-04-23T21:26:35Z","timestamp":1619213195000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["Opinion dynamics and consensus achievement strategy based on reinforcement learning"],"prefix":"10.1109","author":[{"given":"Mingwei","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangshun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Decui","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/0022250X.1990.9990069"},{"key":"ref11","article-title":"Deep recurrent Q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"Computer Science"},{"key":"ref12","first-page":"1","article-title":"Opinion dynamics and bounded confidence models, analysis and simulation","volume":"5","author":"hegselmann","year":"2002","journal-title":"Journal of Artificial Societies & Social Simulation"},{"key":"ref13","author":"howard","year":"1960","journal-title":"Dynamic Programming and Markov Processes"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2015.08.010"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/59.867150"},{"key":"ref19","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction Adaptive Computations and Machine Learning"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2307\/2285509"},{"key":"ref3","article-title":"Deep Reinforcement Learning Variants of Multi-Agent Learning Algorithms","author":"castaneda","year":"2016","journal-title":"masters thesis"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2016.03.001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1142\/S0129183118500468"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2017.11.009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2017.02.052"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1073\/pnas.38.8.716","article-title":"On the theory of dynamic programming","volume":"38","author":"bellman","year":"1952","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.socnet.2012.06.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/h0046123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1037\/0003-066X.53.10.1125"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/cplx.10031"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"}],"event":{"name":"2020 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)","location":"Louisville, KY, USA","start":{"date-parts":[[2020,12,9]]},"end":{"date-parts":[[2020,12,11]]}},"container-title":["2020 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9408637\/9408642\/09408808.pdf?arnumber=9408808","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T01:02:06Z","timestamp":1656637326000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9408808\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,9]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/isspit51521.2020.9408808","relation":{},"subject":[],"published":{"date-parts":[[2020,12,9]]}}}