{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T11:41:06Z","timestamp":1775562066077,"version":"3.50.1"},"reference-count":44,"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":["U19B2044"],"award-info":[{"award-number":["U19B2044"]}],"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":["61836011"],"award-info":[{"award-number":["61836011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tg.2022.3158649","type":"journal-article","created":{"date-parts":[[2022,3,11]],"date-time":"2022-03-11T20:25:21Z","timestamp":1647030321000},"page":"315-325","source":"Crossref","is-referenced-by-count":5,"title":["Model-Free Neural Counterfactual Regret Minimization With Bootstrap Learning"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4262-639X","authenticated-orcid":false,"given":"Weiming","family":"Liu","sequence":"first","affiliation":[{"name":"School of Data Science, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2332-3959","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3128-4598","authenticated-orcid":false,"given":"Julian","family":"Togelius","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, New York University, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-75538-8_7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2200894"},{"key":"ref6","first-page":"689","article-title":"Safe and nested subgame solving for imperfect-information games","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Brown","year":"2017"},{"key":"ref7","first-page":"3426","article-title":"Actor-critic policy optimization in partially observable multiagent environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Srinivasan","year":"2018"},{"key":"ref8","first-page":"1729","article-title":"Regret minimization in games with incomplete information","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Zinkevich","year":"2007"},{"key":"ref9","first-page":"805","article-title":"Fictitious self-play in extensive-form games","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"37","author":"Heinrich","year":"2015"},{"key":"ref10","first-page":"335","article-title":"Double-oracle algorithm for computing an exact Nash equilibrium in zero-sum extensive-form games","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Bosansk","year":"2013"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0452"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.aao1733"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref15","first-page":"271","article-title":"Evaluating state-space abstractions in extensive-form games","volume-title":"Proc. Int. Conf. Auton. Agents Multi-Agent Syst.","author":"Johanson","year":"2013"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v29i1.9445"},{"key":"ref17","article-title":"Using regret estimation to solve games compactly","author":"Morrill","year":"2016"},{"key":"ref18","first-page":"793","article-title":"Deep counterfactual regret minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"97","author":"Brown","year":"2019"},{"key":"ref19","article-title":"Double neural counterfactual regret minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Li","year":"2020"},{"key":"ref20","article-title":"DREAM: Deep regret minimization with advantage baselines and model-free learning","author":"Steinberger","year":"2006"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10056"},{"key":"ref23","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8810"},{"key":"ref25","first-page":"7663","article-title":"Depth-limited solving for imperfect-information games","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Brown","year":"2018"},{"key":"ref26","article-title":"Solving large imperfect information games using CFR+","author":"Tammelin","year":"2014"},{"key":"ref27","article-title":"Single deep counterfactual regret minimization","author":"Steinberger","year":"2019"},{"key":"ref28","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"Heinrich","year":"2016"},{"key":"ref29","article-title":"The advantage regret-matching actor-critic","author":"Gruslys","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012157"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/66"},{"key":"ref32","first-page":"1078","article-title":"Monte Carlo sampling for regret minimization in extensive games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lanctot","year":"2009"},{"key":"ref33","first-page":"837","article-title":"Efficient Nash equilibrium approximation through Monte Carlo counterfactual regret minimization","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Johanson","year":"2012"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8241"},{"issue":"34","key":"ref35","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":"ref36","first-page":"550","article-title":"Bayes Bluff: Opponent modeling in poker","volume-title":"Proc. Conf. Uncertainty Artif. Intell.","author":"Southey","year":"2005"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref38","article-title":"OpenSpiel: A framework for reinforcement learning in games","author":"Lanctot","year":"2019"},{"key":"ref39","article-title":"Eqilibrium approximation quality of current no-limit poker bots","volume-title":"Proc. Workshops AAAI Conf. Artif. Intell.","author":"Lis","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16676"},{"key":"ref41","first-page":"2392","article-title":"Low-variance and zero-variance baselines for extensive-form games","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Davis","year":"2020"},{"key":"ref42","first-page":"5222","article-title":"Optimistic regret minimization for extensive-form games via dilated distance-generating functions","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Farina","year":"2019"},{"key":"ref43","article-title":"A unified view of large-scale zero-sum equilibrium computation","volume-title":"Proc. Workshops AAAI Conf. Artif. Intell.","author":"Waugh","year":"2015"},{"key":"ref44","first-page":"263","article-title":"Competing in the dark: An efficient algorithm for bandit linear optimization","volume-title":"Proc. Conf. Learn. Theory","author":"Abernethy","year":"2008"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10251473\/09733210.pdf?arnumber=9733210","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:14:53Z","timestamp":1705536893000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9733210\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":44,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3158649","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}