{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:27:17Z","timestamp":1779384437028,"version":"3.53.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0101005"],"award-info":[{"award-number":["2018AAA0101005"]}]},{"name":"National Key Research and Development Program of China","award":["2018AAA0102404"],"award-info":[{"award-number":["2018AAA0102404"]}]},{"name":"Huawei Noah's Ark Lab","award":["YBN2020075035"],"award-info":[{"award-number":["YBN2020075035"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1109\/tg.2020.3022698","type":"journal-article","created":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T20:33:05Z","timestamp":1599683585000},"page":"5-15","source":"Crossref","is-referenced-by-count":27,"title":["Enhanced Rolling Horizon Evolution Algorithm With Opponent Model Learning: Results for the Fighting Game AI Competition"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2481-4119","authenticated-orcid":false,"given":"Zhentao","family":"Tang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3180-7451","authenticated-orcid":false,"given":"Simon M.","family":"Lucas","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Computer Engineering (EECS), Queen Mary University of London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref4","first-page":"19","article-title":"Self-play Monte-Carlo tree search in computer poker","volume-title":"Proc. 28th AAAI-14 Conf. Artif. Intell.","author":"Heinrich","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2463372.2463413"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2015.2402393"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.9869"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080420"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE.2013.6664844"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63519-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ACIT-CSI.2015.18"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24589-8_7"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE.2016.7800536"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080432"},{"issue":"6","key":"ref15","first-page":"701","article-title":"Review of deep reinforcement learning and discussions on the development of computer Go","volume":"33","author":"Zhao","year":"2016","journal-title":"Control Theory Appl."},{"issue":"12","key":"ref16","first-page":"1529","article-title":"Recent progress of deep reinforcement learning: From AlphaGo to AlphaGo Zero","volume":"34","author":"Tang","year":"2017","journal-title":"Control Theory"},{"key":"ref17","article-title":"A survey of deep reinforcement learning in video games","author":"Shao","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628682"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490423"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIST.2018.8426160"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080451"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490437"},{"key":"ref24","first-page":"255","article-title":"Online implicit agent modelling","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Bard","year":"2013"},{"key":"ref25","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. Int.Conf. Mach. Learn.","author":"He","year":"2016"},{"key":"ref26","first-page":"533","article-title":"Game theory-based opponent modeling in large imperfect-information games","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","volume":"2","author":"Ganzfried","year":"2011"},{"key":"ref27","first-page":"4215","article-title":"Machine theory of mind","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rabinowitz","year":"2018"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-55849-3_28"},{"issue":"3-4","key":"ref29","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"ref30","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"Sutton","year":"2000","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"ref31","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume-title":"Proc. 13th Int. Conf. Artif. Intell. Statist.","author":"Glorot","year":"2010"},{"key":"ref32","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3205651.3205695"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20257-6_12"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3319619.3326772"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490377"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10075412\/09190073.pdf?arnumber=9190073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:54:53Z","timestamp":1704844493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9190073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2020.3022698","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3]]}}}