{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T09:10:02Z","timestamp":1751015402183,"version":"3.41.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T00:00:00Z","timestamp":1745971200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T00:00:00Z","timestamp":1745971200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00521-025-11262-x","type":"journal-article","created":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T05:49:16Z","timestamp":1745992156000},"page":"13525-13546","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive multi-player poker policy learning based on opponent style modeling"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-555X","authenticated-orcid":false,"given":"Daming","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xudong","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhui","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,30]]},"reference":[{"issue":"2","key":"11262_CR1","doi-asserted-by":"publisher","first-page":"93","DOI":"10.3233\/ICG-1997-20207","volume":"20","author":"J Schaeffer","year":"1997","unstructured":"Schaeffer J (1997) One Jump Ahead: Challenging Human Supremacy in Checkers[J]. ICGA journal 20(2):93\u201393","journal-title":"ICGA journal"},{"issue":"1\u20132","key":"11262_CR2","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/S0004-3702(01)00129-1","volume":"134","author":"M Campbell","year":"2002","unstructured":"Campbell M, Hoane AJ, Hsu FH (2002) Deep Blue[J]. Artif Intell 134(1\u20132):57\u201383","journal-title":"Artif Intell"},{"key":"11262_CR3","doi-asserted-by":"crossref","unstructured":"D Silver, Huang A, Maddison C J, et al. Mastering the game of Go with deep neural networks and tree search[J]. Nature, 2016, 529, 484\u2013489.","DOI":"10.1038\/nature16961"},{"issue":"7676","key":"11262_CR4","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K et al (2017) Mastering the game of Go without human knowledge[J]. Nature 550(7676):354\u2013359","journal-title":"Nature"},{"issue":"5\u20136","key":"11262_CR5","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1016\/j.artint.2010.12.005","volume":"175","author":"J Rubin","year":"2011","unstructured":"Rubin J, Watson I (2011) Computer poker: A review[J]. Artif Intell 175(5\u20136):958\u2013987","journal-title":"Artif Intell"},{"issue":"6218","key":"11262_CR6","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1126\/science.1259433","volume":"347","author":"M Bowling","year":"2015","unstructured":"Bowling M, Burch N, Johanson M et al (2015) Heads-up limit hold\u2019em poker is solved[J]. Science 347(6218):145\u2013149","journal-title":"Science"},{"key":"11262_CR7","doi-asserted-by":"crossref","unstructured":"Morav\u010d\u00edk, Matej, Schmid M, Burch N, et al. DeepStack: Expert-level artificial intelligence in heads-up no-limit poker[J]. Science, 2017, 356(6337):508\u2013513.","DOI":"10.1126\/science.aam6960"},{"issue":"6374","key":"11262_CR8","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1126\/science.aao1733","volume":"359","author":"N Brown","year":"2018","unstructured":"Brown N, Sandholm T (2018) Superhuman AI for heads-up no-limit poker: Libratus beats top professionals[J]. Science 359(6374):418\u2013424","journal-title":"Science"},{"issue":"6456","key":"11262_CR9","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1126\/science.aay2400","volume":"365","author":"N Brown","year":"2019","unstructured":"Brown N, Sandholm T (2019) Superhuman AI for multiplayer poker[J]. Science 365(6456):885\u2013890","journal-title":"Science"},{"issue":"6","key":"11262_CR10","doi-asserted-by":"publisher","first-page":"774","DOI":"10.3390\/e24060774","volume":"24","author":"D Shi","year":"2022","unstructured":"Shi D, Guo X, Liu Y et al (2022) Optimal policy of multiplayer poker via actor-critic reinforcement learning[J]. Entropy 24(6):774","journal-title":"Entropy"},{"key":"11262_CR11","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","volume":"258","author":"SV Albrecht","year":"2018","unstructured":"Albrecht SV, Stone P (2018) Autonomous agents modelling other agents: A comprehensive survey and open problems[J]. Artif Intell 258:66\u201395","journal-title":"Artif Intell"},{"issue":"1","key":"11262_CR12","first-page":"374","volume":"13","author":"GW Brown","year":"1951","unstructured":"Brown GW (1951) Iterative solution of games by fictitious play[J]. Act Anal Prod Allocation 13(1):374","journal-title":"Act Anal Prod Allocation"},{"key":"11262_CR13","unstructured":"Fudenberg D, Levine D K. The theory of learning in games[M]. MIT press, 1998."},{"issue":"746\u2013752","key":"11262_CR14","first-page":"2","volume":"1998","author":"C Claus","year":"1998","unstructured":"Claus C, Boutilier C (1998) The dynamics of reinforcement learning in cooperative multiagent systems[J]. AAAI\/IAAI 1998(746\u2013752):2","journal-title":"AAAI\/IAAI"},{"key":"11262_CR15","doi-asserted-by":"crossref","unstructured":"Lockett A J, Chen C L, Miikkulainen R. Evolving explicit opponent models in game playing[C]\/\/Proceedings of the 9th annual conference on Genetic and evolutionary computation. 2007: 2106\u20132113.","DOI":"10.1145\/1276958.1277367"},{"key":"11262_CR16","unstructured":"He H, Boyd-Graber J, Kwok K, et al. Opponent modeling in deep reinforcement learning[C]\/\/International conference on machine learning. PMLR, 2016: 1804\u20131813."},{"key":"11262_CR17","unstructured":"Schadd F, Bakkes S, Spronck P. Opponent Modeling in Real-Time Strategy Games[C]\/\/GAMEON. 2007: 61\u201370."},{"key":"11262_CR18","doi-asserted-by":"crossref","unstructured":"Synnaeve G, Bessiere P. A Bayesian model for opening prediction in RTS games with application to StarCraft[C]\/\/2011 IEEE Conference on Computational Intelligence and Games (CIG\u201911). IEEE, 2011: 281\u2013288.","DOI":"10.1109\/CIG.2011.6032018"},{"key":"11262_CR19","doi-asserted-by":"crossref","unstructured":"Steffens T. Feature-Based Declarative Opponent-Modelling[C]\/\/Springer Berlin Heidelberg. Springer Berlin Heidelberg, 2003:125\u2013136.","DOI":"10.1007\/978-3-540-25940-4_11"},{"key":"11262_CR20","unstructured":"Pynadath D V, Wellman M P, Probabilistic state-dependent grammars for plan recognition, in: Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, 2000, pp. 507\u2013514."},{"key":"11262_CR21","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/BF00849553","volume":"7","author":"MF McTear","year":"1993","unstructured":"McTear MF (1993) User modelling for adaptive computer systems: a survey of recent developments[J]. Artif Intell Rev 7:157\u2013184","journal-title":"Artif Intell Rev"},{"key":"11262_CR22","unstructured":"Vidal J M, Durfee E H. Recursive Agent Modeling Using Limited Rationality[C]\/\/ICMAS. 1995: 376\u2013383."},{"key":"11262_CR23","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1007\/s10458-014-9261-5","volume":"29","author":"E Sonu","year":"2015","unstructured":"Sonu E, Doshi P (2015) Scalable solutions of interactive POMDPs using generalized and bounded policy iteration[J]. Auton Agent Multi-Agent Syst 29:455\u2013494","journal-title":"Auton Agent Multi-Agent Syst"},{"key":"11262_CR24","doi-asserted-by":"crossref","unstructured":"Billings D, Davidson A, Schauenberg T, et al. Game-tree search with adaptation in stochastic imperfect-information games[C]\/\/Computers and Games: 4th International Conference, CG 2004, Ramat-Gan, Israel, July 5\u20137, 2004. Revised Papers 4. Springer Berlin Heidelberg, 2006: 21\u201334.","DOI":"10.1007\/11674399_2"},{"key":"11262_CR25","unstructured":"Southey F, Bowling M P, Larson B, et al., Bayes\u2019 bluff: opponent modeling in poker, in: Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence, 2005, pp. 550\u2013558."},{"key":"11262_CR26","unstructured":"Ganzfried S, Sandholm T. Game theory-based opponent modeling in large imperfect-information games[C]\/\/The 10th International Conference on Autonomous Agents and Multiagent Systems-Volume 2. 2011: 533\u2013540."},{"issue":"1","key":"11262_CR27","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1109\/TCIAIG.2015.2491611","volume":"9","author":"R Mealing","year":"2015","unstructured":"Mealing R, Shapiro JL (2015) Opponent modeling by expectation\u2013maximization and sequence prediction in simplified poker[J]. IEEE Transactions on Computational Intelligence and AI in Games 9(1):11\u201324","journal-title":"IEEE Transactions on Computational Intelligence and AI in Games"},{"key":"11262_CR28","doi-asserted-by":"crossref","unstructured":"Te\u00f3filo L F, Passos N, Reis L P, et al. Adapting strategies to opponent models in incomplete information games: a reinforcement learning approach for poker[C]\/\/Autonomous and Intelligent Systems: Third International Conference, AIS 2012, Aveiro, Portugal, June 25\u201327, 2012. Proceedings. Springer Berlin Heidelberg, 2012: 220\u2013227.","DOI":"10.1007\/978-3-642-31368-4_26"},{"key":"11262_CR29","unstructured":"Sklansky D, Miller E. No Limit Hold\u2019em: Theory and Practice[M]. Two Plus Two Publishing LLC, 2006. Pages 208\u2013209."},{"key":"11262_CR30","unstructured":"Krieger L, Llc C. Hold\u2019em Excellence-From Beginner to Winner[M]. 2009. Chapter 5, pages 39 - 43."},{"key":"11262_CR31","doi-asserted-by":"crossref","unstructured":"Yao J, Zhang Z, Xia L, et al. Solving imperfect information poker games using Monte Carlo search and POMDP models[C]\/\/2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS). IEEE, 2020: 1060\u20131065.","DOI":"10.1109\/DDCLS49620.2020.9275053"},{"key":"11262_CR32","doi-asserted-by":"crossref","unstructured":"Xu Y, He K, Hu S, et al. A reinforcement learning framework based on regret minimization for approximating best response in fictitious self-play[C]\/\/2022 IEEE 24th Int Conf on High Performance Computing & Communications; 8th Int Conf on Data Science & Systems; 20th Int Conf on Smart City; 8th Int Conf on Dependability in Sensor, Cloud & Big Data Systems & Application (HPCC\/DSS\/SmartCity\/DependSys). IEEE, 2022: 1728\u20131735.","DOI":"10.1109\/HPCC-DSS-SmartCity-DependSys57074.2022.00261"},{"key":"11262_CR33","doi-asserted-by":"crossref","unstructured":"Ramirez A, Reinman S, Norouzi N. Pokerbot: Hand strength reinforcement learning[C]\/\/2019 IEEE International Symposium on INnovations in Intelligent SysTems and Applications (INISTA). IEEE, 2019: 1\u20136.","DOI":"10.1109\/INISTA.2019.8778267"},{"key":"11262_CR34","unstructured":"Bosilj P, Pala\u0161ek P, Popovi\u0107 B, et al. Simulation of a Texas Hold\u2019Em poker player[C]\/\/2011 Proceedings of the 34th International Convention MIPRO. IEEE, 2011: 1628\u20131633."},{"key":"11262_CR35","doi-asserted-by":"crossref","unstructured":"Wu D. Multi-Agent Reinforcement Learning Investigation Based on Football Games[C]\/\/2023 IEEE 3rd International Conference on Computer Communication and Artificial Intelligence (CCAI). IEEE, 2023: 26\u201329.","DOI":"10.1109\/CCAI57533.2023.10201281"},{"key":"11262_CR36","doi-asserted-by":"crossref","unstructured":"Qin S, Zhang L, Qi S, et al. EFDO: Solving Extensive-Form Games Based On Double Oracle[C]\/\/2022 4th International Conference on Data Intelligence and Security (ICDIS). IEEE, 2022: 382\u2013387.","DOI":"10.1109\/ICDIS55630.2022.00064"},{"key":"11262_CR37","doi-asserted-by":"crossref","unstructured":"Xu J, Chen S. A Neuroevolutionary Approach for Opponent Modeling and Exploitation in No-limit Texas Hold\u2019em Poker[C]\/\/2021 China Automation Congress (CAC). IEEE, 2021: 2270\u20132275.","DOI":"10.1109\/CAC53003.2021.9727922"},{"key":"11262_CR38","doi-asserted-by":"crossref","unstructured":"Rebstock D, Solinas C, Buro M. Learning policies from human data for skat[C]\/\/2019 IEEE Conference on Games (CoG). IEEE, 2019: 1\u20138.","DOI":"10.1109\/CIG.2019.8848125"},{"key":"11262_CR39","doi-asserted-by":"crossref","unstructured":"Luo Q, Tan T P. RARSMSDou: Master the Game of DouDiZhu With Deep Reinforcement Learning Algorithms[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2023.","DOI":"10.1109\/TETCI.2023.3303251"},{"key":"11262_CR40","doi-asserted-by":"crossref","unstructured":"Yan X, Xia L, Yang J, et al. Opponent modeling in poker games[C]\/\/2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS). IEEE, 2020: 1090\u20131097.","DOI":"10.1109\/DDCLS49620.2020.9275228"},{"key":"11262_CR41","doi-asserted-by":"crossref","unstructured":"Wu Z, Li K, Xu H, et al. L2E: Learning to exploit your opponent[C]\/\/2022 International Joint Conference on Neural Networks (IJCNN). IEEE, 2022: 1\u20138.","DOI":"10.1109\/IJCNN55064.2022.9892077"},{"issue":"5","key":"11262_CR42","doi-asserted-by":"publisher","first-page":"2966","DOI":"10.1109\/TCYB.2022.3228812","volume":"54","author":"Z Ge","year":"2022","unstructured":"Ge Z, Yang S, Tian P et al (2022) Modeling rationality: Toward better performance against unknown agents in sequential games[J]. IEEE Transactions on Cybernetics 54(5):2966\u20132977","journal-title":"IEEE Transactions on Cybernetics"},{"key":"11262_CR43","doi-asserted-by":"crossref","unstructured":"Weilin Y, Zhenzhen H, Tingting W, et al. Opponent-Restricted Response Solving on Texas Hold\u2019em Poker[C]\/\/2021 China Automation Congress (CAC). IEEE, 2021: 2467\u20132473.","DOI":"10.1109\/CAC53003.2021.9727647"},{"key":"11262_CR44","doi-asserted-by":"crossref","unstructured":"Baker R J S, Cowling P I. Bayesian opponent modeling in a simple poker environment[C]\/\/2007 IEEE Symposium on Computational Intelligence and Games. IEEE, 2007: 125\u2013131.","DOI":"10.1109\/CIG.2007.368088"},{"key":"11262_CR45","doi-asserted-by":"crossref","unstructured":"Baker R J S, Cowling P I, Randall T W G, et al. Can opponent models aid poker player evolution?[C]\/\/2008 IEEE Symposium On Computational Intelligence and Games. Ieee, 2008: 23\u201330.","DOI":"10.1109\/CIG.2008.5035617"},{"key":"11262_CR46","doi-asserted-by":"crossref","unstructured":"Lockett A J, Miikkulainen R. Evolving opponent models for Texas hold\u2019Em[C]\/\/2008 IEEE Symposium On Computational Intelligence and Games. IEEE, 2008: 31\u201338.","DOI":"10.1109\/CIG.2008.5035618"},{"issue":"12","key":"11262_CR47","doi-asserted-by":"publisher","first-page":"7635","DOI":"10.1109\/TCYB.2022.3186886","volume":"53","author":"H Fang","year":"2022","unstructured":"Fang H, Zhang M, He S et al (2022) Solving the zero-sum control problem for tidal turbine system: An online reinforcement learning approach[J]. IEEE Transactions on Cybernetics 53(12):7635\u20137647","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"2","key":"11262_CR48","doi-asserted-by":"publisher","first-page":"549","DOI":"10.1109\/TNNLS.2019.2905715","volume":"31","author":"S He","year":"2019","unstructured":"He S, Fang H, Zhang M et al (2019) Adaptive optimal control for a class of nonlinear systems: The online policy iteration approach[J]. IEEE transactions on neural networks and learning systems 31(2):549\u2013558","journal-title":"IEEE transactions on neural networks and learning systems"},{"issue":"6419","key":"11262_CR49","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver D, Hubert T, Schrittwieser J et al (2018) A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play[J]. Science 362(6419):1140\u20131144","journal-title":"Science"},{"key":"11262_CR50","unstructured":"Heinrich J, Lanctot M, Silver D. Fictitious self-play in extensive-form games[C]\/\/International conference on machine learning. PMLR, 2015: 805\u2013813."},{"key":"11262_CR51","unstructured":"elbrede S. The Statistics of Poker Data Mining Statistics Applied to Small Stakes No Limit Hold\u2019em[M]. 2015."}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11262-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11262-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11262-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:29:08Z","timestamp":1751012948000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11262-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,30]]},"references-count":51,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11262"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11262-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2025,4,30]]},"assertion":[{"value":"1 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No funding was received for conducting this study. The authors have no relevant financial or nonfinancial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}]}}