{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:37:30Z","timestamp":1767339450463,"version":"3.43.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"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":["62293541","62136008","62425117"],"award-info":[{"award-number":["62293541","62136008","62425117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4232056"],"award-info":[{"award-number":["4232056"]}],"id":[{"id":"10.13039\/501100005089","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484514"],"award-info":[{"award-number":["20240484514"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,8]]},"DOI":"10.1109\/tnnls.2024.3516693","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T14:38:13Z","timestamp":1734532693000},"page":"13859-13873","source":"Crossref","is-referenced-by-count":3,"title":["Last-Iterate Convergence to Approximate Nash Equilibria in Multiplayer Imperfect Information Games"],"prefix":"10.1109","volume":"36","author":[{"given":"Runyu","family":"Lu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5384-423X","authenticated-orcid":false,"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8218-9633","authenticated-orcid":false,"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5216-3181","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6111-340X","authenticated-orcid":false,"given":"You","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.aao1733"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316779309"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511800481"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-021-00577-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3270444"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2020.3022698"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"issue":"1","key":"ref9","first-page":"374","article-title":"Iterative solution of games by fictitious play","volume":"13","author":"Brown","year":"1951","journal-title":"Act. Anal. Prod Allocation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0262.00153"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.2307\/1969530"},{"article-title":"Abstraction in large extensive games","year":"2009","author":"Waugh","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3280186"},{"key":"ref14","first-page":"805","article-title":"Fictitious self-play in extensive-form games","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Heinrich"},{"key":"ref15","first-page":"1","article-title":"Regret minimization in games with incomplete information","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Zinkevich"},{"key":"ref16","article-title":"Deep reinforcement learning from self-play in imperfect-information games","author":"Heinrich","year":"2016","journal-title":"arXiv:1603.01121"},{"key":"ref17","first-page":"793","article-title":"Deep counterfactual regret minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Brown"},{"article-title":"Monte Carlo sampling and regret minimization for equilibrium computation and decision-making in large extensive form games","year":"2013","author":"Lanctot","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/bfb0087009"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139173179"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611975031.172"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0025-5564(78)90077-9"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4086\/toc.2012.v008a006"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1561\/2400000013"},{"key":"ref26","first-page":"492","article-title":"Neural replicator dynamics: Multiagent learning via hedging policy gradients","volume-title":"Proc. 19th Int. Conf. Auto. Agents MultiAgent Syst.","author":"Hennes"},{"key":"ref27","first-page":"8525","article-title":"From poincar\u00e9 recurrence to convergence in imperfect information games: Finding equilibrium via regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Perolat"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2020.2978037"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012903437976"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1006\/game.1995.1023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2018.2833140"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3204543"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref35","first-page":"17057","article-title":"Combining deep reinforcement learning and search for imperfect-information games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3215629"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3208611"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3251653"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3228812"},{"key":"ref40","first-page":"709","article-title":"Dynamic programming for partially observable stochastic games","volume-title":"Proc. AAAI","volume":"4","author":"Hansen"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012029"},{"key":"ref42","first-page":"1","article-title":"Last-iterate convergence: Zero-sum games and constrained min-max optimization","volume-title":"Proc. 10th Innov. Theor. Comput. Sci.","author":"Daskalakis"},{"key":"ref43","first-page":"14293","article-title":"Last-iterate convergence in extensive-form games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Lee"},{"key":"ref44","first-page":"1","article-title":"Approximating nash equilibria in normal-form games via stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gemp"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10581"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/080720826"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1461928.1461951"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0163"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-5315-8"},{"key":"ref50","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref51","first-page":"1","article-title":"Bandit learning in concave N-person games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Bravo"},{"key":"ref52","first-page":"20580","article-title":"Divergence-regularized multi-agent actor-critic","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Su"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jet.2009.01.007"},{"volume-title":"Population Games and Evolutionary Dynamics","year":"2010","author":"Sandholm","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1254-8"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881727-010"},{"key":"ref57","first-page":"550","article-title":"Bayes\u2019 bluff: Opponent modelling in poker","volume-title":"Proc. 21st Conf. Uncertainty Artif. Intell.","author":"Southey"},{"key":"ref58","article-title":"The equivalence of dynamic and strategic stability under regularized learning in games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Boone"},{"key":"ref59","first-page":"6337","article-title":"Kernelized multiplicative weights for 0\/1-polyhedral games: Bridging the gap between learning in extensive-form and normal-form games","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Farina"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1126\/science.1259433"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i6.16676"},{"key":"ref62","first-page":"1","article-title":"Regret matching+: (In)Stability and fast convergence in games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Farina"},{"key":"ref63","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3309608"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3025491"},{"volume-title":"Mathematical Economics","year":"1985","author":"Takayama","key":"ref70"},{"volume-title":"Nonlinear Systems","year":"2002","author":"Khalil","key":"ref71"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11114436\/10806634.pdf?arnumber=10806634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,6]],"date-time":"2025-08-06T18:00:48Z","timestamp":1754503248000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8]]},"references-count":71,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3516693","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,8]]}}}