{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:11:21Z","timestamp":1781021481389,"version":"3.54.1"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602539"],"award-info":[{"award-number":["61602539"]}],"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":["61873291"],"award-info":[{"award-number":["61873291"]}],"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":["61773416"],"award-info":[{"award-number":["61773416"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Minzu University of China (MUC) 111 Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2019]]},"DOI":"10.1109\/access.2019.2938240","type":"journal-article","created":{"date-parts":[[2019,8,30]],"date-time":"2019-08-30T00:07:40Z","timestamp":1567123660000},"page":"121922-121930","source":"Crossref","is-referenced-by-count":25,"title":["A Reinforcement Learning Model Based on Temporal Difference Algorithm"],"prefix":"10.1109","volume":"7","author":[{"given":"Xiali","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyu","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-634X","authenticated-orcid":false,"given":"Licheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","first-page":"3338","article-title":"Deep learning for real-time atari game play using offline monte-carlo tree search planning","author":"guo","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1126\/science.aao1733","article-title":"Superhuman AI for heads-up no-limit poker: Libratus beats top professionals","volume":"359","author":"noam","year":"2018","journal-title":"Science"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref12","first-page":"5","article-title":"The research of tibetan chess","volume":"9","author":"shotwell","year":"1994","journal-title":"J Tibet Univ"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/DASC-PICom-DataCom-CyberSciTec.2016.33"},{"key":"ref14","article-title":"Design and implementation of jiu game prototype system and multimedia courseware","author":"deng","year":"2017"},{"key":"ref15","first-page":"1","article-title":"Strategy research based on chess shapes for tibetan JIU computer game","volume":"40","author":"li","year":"2018","journal-title":"ICGA J"},{"key":"ref16","first-page":"28","article-title":"Evolutionary programming for goal-driven dynamic planning","volume":"4739","author":"vaccaro","year":"2002","journal-title":"Applied Comput Inte and SC"},{"key":"ref17","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":"ref18","first-page":"278","article-title":"9*9 go machine game system with time difference algorithm","volume":"7","author":"niu","year":"2012","journal-title":"CAAI Trans Intell Syst"},{"key":"ref19","first-page":"529","article-title":"Temporal difference learning applied to a high-performance game-playing program","author":"schaeffer","year":"2001","journal-title":"Proc 17th Int Joint Conf Artif Intell"},{"key":"ref28","first-page":"335","article-title":"Value-difference based exploration: Adaptive control between epsilon-greedy and softmax","author":"tokic","year":"2011","journal-title":"Proc Annu Conf Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref27","first-page":"825","article-title":"Sarsa(\n$\\lambda$\n) algorithm based on heuristic function","volume":"44","author":"pengwei","year":"2016","journal-title":"Digital Computer Engineering"},{"key":"ref3","article-title":"Behavioral modeling and linearization of wideband RF power amplifiers using BiLSTM networks for 5G wireless systems","author":"sun","year":"0","journal-title":"IEEE Trans Veh Technol"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC.2008.694"},{"key":"ref5","author":"hsu","year":"2004","journal-title":"Behind Deep Blue Building the Computer that Defeated the World Chess Champion"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref7","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2900460"},{"key":"ref9","first-page":"689","article-title":"Safe and nested subgame solving for imperfect-information games","author":"brown","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2848294"},{"key":"ref20","first-page":"221","article-title":"A reinforcement learning-based adaptive learning system","author":"shawky","year":"2018","journal-title":"Proc 1st Int Conf Adv Mach Learn Technol Appl"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00176"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2851783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HUMANOIDS.2017.8246959"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2010.2100395"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.2298\/CSIS170107029Z"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CGames.2012.6314567"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8600701\/08819952.pdf?arnumber=8819952","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,27]],"date-time":"2022-01-27T00:44:22Z","timestamp":1643244262000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8819952\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/access.2019.2938240","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019]]}}}