{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T21:45:46Z","timestamp":1767649546302,"version":"3.37.3"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/cog51982.2022.9893584","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"345-352","source":"Crossref","is-referenced-by-count":6,"title":["Speedup Training Artificial Intelligence for Mahjong via Reward Variance Reduction"],"prefix":"10.1109","author":[{"given":"Jinqiu","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Shuang","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Tencent,Shenzhen,China"}]},{"given":"Haobo","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Tencent,Shenzhen,China"}]},{"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Tencent,Shenzhen,China"}]},{"given":"Enmin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences,Beijing,China"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3197091.3197099"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1126\/science.aam6960","article-title":"DeepStack: Expert-level artificial intelligence in heads-up no-limit poker","volume":"356","author":"moravcik","year":"2017","journal-title":"Science"},{"key":"ref11","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":"brown","year":"2018","journal-title":"Science"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref13","first-page":"1729","article-title":"Regret minimization in games with incomplete information","author":"zinkevich","year":"2007","journal-title":"Advances in neural information processing systems"},{"key":"ref14","first-page":"1078","article-title":"Monte Carlo sampling for regret minimization in extensive games","author":"lanctot","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref15","first-page":"35","article-title":"Slumbot NL: Solving large games with counterfactual regret minimization using sampling and distributed processing","author":"jackson","year":"2013","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref16","first-page":"17 057","article-title":"Combining deep reinforcement learning and search for imperfect-information games","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref17","first-page":"1","article-title":"Alphaholdem: High-performance artificial intelligence for heads-up no-limit texas hold’em from end-to-end reinforcement learning","author":"zhao","year":"2022","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/176"},{"key":"ref19","first-page":"12 333","article-title":"DouZero: Mastering Doudizhu with self-play deep reinforcement learning","author":"zha","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref27","first-page":"1","article-title":"Actor-critic policy optimization in a large-scale imperfect-information game","author":"fu","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2010.12.005"},{"key":"ref29","first-page":"7515","article-title":"How does batch normalization help optimization?","author":"santurkar","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref8","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/science.1259433"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00129-1"},{"key":"ref20","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref22","first-page":"621","article-title":"Towards playing full MOBA games with deep reinforcement learning","author":"ye","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"arXiv preprint arXiv 1912 06680"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3036471"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2015.7317929"},{"key":"ref26","article-title":"Suphx: Mastering Mahjong with deep reinforcement learning","author":"li","year":"2020","journal-title":"arXiv preprint arXiv 2003 13874"},{"key":"ref25","first-page":"2410","article-title":"Realizing a four-player computer Mahjong program by supervised learning with isolated multi-player aspects","volume":"55","author":"mizukami","year":"2014","journal-title":"Transactions of Information Processing Society of Japan"}],"event":{"name":"2022 IEEE Conference on Games (CoG)","start":{"date-parts":[[2022,8,21]]},"location":"Beijing, China","end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9893561\/9893544\/09893584.pdf?arnumber=9893584","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:25:44Z","timestamp":1665433544000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893584\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893584","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}