{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T05:11:29Z","timestamp":1746508289121,"version":"3.37.3"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&amp;D Program of China","award":["2022ZD0119802"],"award-info":[{"award-number":["2022ZD0119802"]}]},{"DOI":"10.13039\/501100004739","name":"Youth Innovation Promotion Association of the Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004739","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU cluster built by MCC Lab of Information Science and Technology Institution, USTC, and the Supercomputing Center of the USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tg.2024.3422396","type":"journal-article","created":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T17:41:54Z","timestamp":1720028514000},"page":"914-926","source":"Crossref","is-referenced-by-count":1,"title":["DanZero+: Dominating the <i>GuanDan<\/i> Game Through Reinforcement Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4610-3545","authenticated-orcid":false,"given":"Youpeng","family":"Zhao","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yudong","family":"Lu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-990X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2846028"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2848913"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2901021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"article-title":"Deep reinforcement learning from self-play in imperfect-information games","year":"2016","author":"Heinrich","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/science.aao1733"},{"article-title":"Suphx: Mastering Mahjong with deep reinforcement learning","year":"2020","author":"Li","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2200894"},{"key":"ref14","first-page":"2021","article-title":"Actor-critic policy optimization in a large-scale imperfect-information game","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Fu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7445"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/176"},{"key":"ref17","first-page":"12333","article-title":"Douzero: Mastering Dou Dizhu with self-play deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zha","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CoG51982.2022.9893710"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC49329.2020.9164725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref21","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zahavy","year":"2018"},{"key":"ref22","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih","year":"2016"},{"issue":"2","key":"ref23","first-page":"229","article-title":"Reinforcement learning: An introduction","volume":"17","author":"Sutton","year":"2018","journal-title":"Robotica"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CoG57401.2023.10333179"},{"key":"ref26","article-title":"An introduction to counterfactual regret minimization","volume-title":"Proc. Educ. Adv. Artif. Intell.","volume":"11","author":"Neller","year":"2013"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/science.1259433"},{"key":"ref28","first-page":"793","article-title":"Deep counterfactual regret minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown","year":"2019"},{"key":"ref29","first-page":"1942","article-title":"Bayesian action decoder for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Foerster","year":"2019"},{"key":"ref30","article-title":"Double neural counterfactual regret minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"article-title":"Single deep counterfactual regret minimization","year":"2019","author":"Steinberger","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref33","first-page":"17057","article-title":"Combining deep reinforcement learning and search for imperfect-information games","volume-title":"Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref34","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.5220\/0006536300290040"},{"key":"ref36","article-title":"Deep neural network approximations for Monte Carlo algorithms","volume-title":"SAM Res. Rep.","volume":"2019","author":"Grohs","year":"2019"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref38","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref39","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Schulman","year":"2016"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CCDC55256.2022.10033565"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/10804819\/10584299.pdf?arnumber=10584299","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:52:34Z","timestamp":1734551554000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10584299\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":40,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tg.2024.3422396","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}