{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:40:39Z","timestamp":1777182039010,"version":"3.51.4"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"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","award":["62272497"],"award-info":[{"award-number":["62272497"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Program of Guangzhou, China","award":["202002020045"],"award-info":[{"award-number":["202002020045"]}]},{"name":"Professorial and Doctoral Initiating Project of Huizhou University","award":["2017JB005"],"award-info":[{"award-number":["2017JB005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tg.2022.3226526","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T23:08:54Z","timestamp":1670281734000},"page":"483-491","source":"Crossref","is-referenced-by-count":4,"title":["WagerWin: An Efficient Reinforcement Learning Framework for Gambling Games"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5405-0642","authenticated-orcid":false,"given":"Haoli","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9758-5698","authenticated-orcid":false,"given":"Hejun","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sun Yat-Sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3675-4977","authenticated-orcid":false,"given":"Guoming","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Huizhou University, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"4292","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref12","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","author":"sunehag","year":"0","journal-title":"Proc 17th Int Conf Auton Agents MultiAgent Syst"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/1969529"},{"key":"ref14","first-page":"1729","article-title":"Regret minimization in games with incomplete information","author":"zinkevich","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref31","article-title":"RLCard: A toolkit for reinforcement learning in card games","author":"zha","year":"2019"},{"key":"ref30","author":"osborne","year":"1994","journal-title":"A Course in Game Theory"},{"key":"ref11","first-page":"1104","article-title":"Implicit quantile networks for distributional reinforcement learning","author":"dabney","year":"0","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref33","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"heinrich","year":"2016"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref32","first-page":"793","article-title":"Deep counterfactual regret minimization","author":"brown","year":"0","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref1","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":"ref17","first-page":"645","article-title":"Solving heads-up limit Texas Hold'em","author":"tammelin","year":"0","journal-title":"Proc 24th Int Joint Conf Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.1259433"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/772"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref24","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref23","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2940261"},{"key":"ref25","first-page":"282","article-title":"Bandit based Monte-Carlo planning","author":"kocsis","year":"0","journal-title":"Proc Mach Learn ECML 2006 17th Eur Conf Mach Learn"},{"key":"ref20","first-page":"1078","article-title":"Monte Carlo sampling for regret minimization in extensive games","author":"lanctot","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref28","first-page":"17057","article-title":"Combining deep reinforcement learning and search for imperfect-information games","volume":"33","author":"brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/176"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20394"},{"key":"ref7","first-page":"12333","article-title":"DouZero: Mastering DouDizhu with self-play deep reinforcement learning","author":"zha","year":"0","journal-title":"Proc 38th Int Conf Mach Learn"},{"key":"ref9","first-page":"449","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"0","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref6","article-title":"Suphx: Mastering Mahjong with deep reinforcement learning","author":"li","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10251473\/09969987.pdf?arnumber=9969987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:12:45Z","timestamp":1696270365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9969987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":33,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3226526","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}