{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T22:13:49Z","timestamp":1766441629907,"version":"3.37.3"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/P505631\/1"],"award-info":[{"award-number":["EP\/P505631\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000770","name":"University of Manchester","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000770","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput. Intell. AI Games"],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/tciaig.2015.2491611","type":"journal-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T18:47:33Z","timestamp":1444934853000},"page":"11-24","source":"Crossref","is-referenced-by-count":15,"title":["Opponent Modeling by Expectation\u2013Maximization and Sequence Prediction in Simplified Poker"],"prefix":"10.1109","volume":"9","author":[{"given":"Richard","family":"Mealing","sequence":"first","affiliation":[]},{"given":"Jonathan L.","family":"Shapiro","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"?Least-squares algorithms ?","year":"0","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2009.00698.x"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015853"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3115\/1620754.1620843"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1977.tb01600.x","article-title":"Maximum likelihood from incomplete data via the EM algorithm","volume":"39","author":"dempster","year":"1977","journal-title":"J Roy Stat Soc"},{"journal-title":"?Monte Carlo sampling and regret minimization for equilibrium computation and decision-making in large extensive form games ?","year":"2013","author":"lanctot","key":"ref37"},{"journal-title":"Learning in dynamic temporal domains using contextual prediction entropy as a guiding principle","year":"2010","author":"jensen","key":"ref36"},{"key":"ref35","first-page":"789","article-title":"Non-stationary policy learning in 2-player zero sum games","author":"jensen","year":"2005","journal-title":"Proc Assoc Adv Artif Intell"},{"journal-title":"Stability of gradient-based learning dynamics in two-agent imperfect-information games","year":"2010","author":"butterworth","key":"ref34"},{"key":"ref10","first-page":"1467","article-title":"Improved opponent modeling in poker","author":"davidson","year":"2000","journal-title":"Proc Int Conf Artificial Intell"},{"key":"ref11","first-page":"1485","article-title":"Bayes-relational learning of opponent models from incomplete information in no-limit poker","author":"ponsen","year":"2008","journal-title":"Proc Assoc Adv Artif Intell Conf"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-05224-8_28"},{"key":"ref13","first-page":"465","article-title":"Similarity-based retrieval and solution re-use policies in the game of Texas Hold?em","author":"rubin","year":"2010","journal-title":"Proc Int Conf Case-Based Reason"},{"key":"ref14","first-page":"343","article-title":"Bayesian poker","author":"korb","year":"1999","journal-title":"Proc Uncertainty Artif Intell"},{"key":"ref15","first-page":"550","article-title":"Bayes? bluff: Opponent modelling in poker","author":"southey","year":"2005","journal-title":"Proc Uncertainty Artif Intell"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2007.368088"},{"key":"ref17","first-page":"159","article-title":"Using counterfactual regret minimization to create competitive multiplayer poker agents","author":"risk","year":"2010","journal-title":"Autonomous Agents and Multiagent Syst"},{"key":"ref18","first-page":"264","article-title":"Data biased robust counter strategies","author":"johanson","year":"2009","journal-title":"Proc Artif Intell Stat"},{"key":"ref19","first-page":"575","article-title":"Computing approximate Nash equilibria and robust best-responses using sampling","volume":"42","author":"ponsen","year":"2011","journal-title":"J Artif Intell Res"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-5193(89)80113-4"},{"key":"ref27","first-page":"1078","author":"lanctot","year":"2009","journal-title":"Neural Information Processing Systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0167-2681(85)90025-3"},{"key":"ref6","first-page":"1321","article-title":"Non-linear dynamics in multiagent reinforcement learning algorithms","author":"abdallah","year":"2008","journal-title":"Autonomous Agents and Multiagent Syst"},{"key":"ref29","first-page":"905","author":"zinkevich","year":"2008","journal-title":"Neural Information Processing Systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref8","first-page":"1128","author":"johanson","year":"2008","journal-title":"Neural Information Processing Systems"},{"key":"ref7","first-page":"927","article-title":"Multi-agent learning with policy prediction","author":"zhang","year":"2010","journal-title":"Proc Assoc Adv Artif Intell Conf"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2307\/1913795"},{"key":"ref9","first-page":"493","article-title":"Opponent modeling in poker","author":"billings","year":"1998","journal-title":"Proc Assoc Adv Artif Intell Conf"},{"journal-title":"The Annual Computer Poker Competition","year":"0","key":"ref1"},{"key":"ref20","first-page":"255","article-title":"Online implicit agent modelling","author":"bard","year":"2013","journal-title":"Autonomous Agents and Multiagent Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v31i4.2311"},{"key":"ref21","first-page":"533","article-title":"Game theory-based opponent modeling in large imperfect-information games","author":"ganzfried","year":"2011","journal-title":"Autonomous Agents and Multiagent Syst"},{"key":"ref24","first-page":"65","article-title":"No-regret learning in extensive-form games with imperfect recall","author":"lanctot","year":"2012","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2010.12.005"},{"journal-title":"Robust Strategies and Counter-Strategies Building A Champion Level Computer Poker Player","year":"2007","author":"johanson","key":"ref26"},{"key":"ref25","first-page":"333","article-title":"Abstraction methods for game theoretic poker","author":"shi","year":"2000","journal-title":"Proc 2nd Int'l Conf CGC"}],"container-title":["IEEE Transactions on Computational Intelligence and AI in Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4804728\/4804729\/07299298.pdf?arnumber=7299298","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T20:48:18Z","timestamp":1718138898000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7299298\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":38,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tciaig.2015.2491611","relation":{},"ISSN":["1943-068X","1943-0698"],"issn-type":[{"type":"print","value":"1943-068X"},{"type":"electronic","value":"1943-0698"}],"subject":[],"published":{"date-parts":[[2017,3]]}}}