{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T20:42:04Z","timestamp":1777322524648,"version":"3.51.4"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000921","name":"European Cooperation in Science and Technology Action","doi-asserted-by":"publisher","award":["CA22145"],"award-info":[{"award-number":["CA22145"]}],"id":[{"id":"10.13039\/501100000921","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3685576","type":"journal-article","created":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T20:05:45Z","timestamp":1776715545000},"page":"61528-61546","source":"Crossref","is-referenced-by-count":0,"title":["Best Agent Identification for General Game Playing"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3867-5842","authenticated-orcid":false,"given":"Matthew","family":"Stephenson","sequence":"first","affiliation":[{"name":"College of Science and Engineering, Flinders University, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4401-0951","authenticated-orcid":false,"given":"Alex","family":"Newcombe","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Flinders University, Adelaide, SA, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8355-636X","authenticated-orcid":false,"given":"\u00c9ric","family":"Piette","sequence":"additional","affiliation":[{"name":"Information and Communication Technologies, Electronics, and Applied Mathematics Institute, UCLouvain, Louvain-la-Neuve, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dennis J. N. J.","family":"Soemers","sequence":"additional","affiliation":[{"name":"Department of Advanced Computing Sciences, Maastricht University, Maastricht, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/2685469"},{"key":"ref2","first-page":"421","article-title":"Atari-5: Distilling the arcade learning environment down to five games","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Aitchison"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8848089"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cig.2017.8080410"},{"key":"ref5","first-page":"41","article-title":"Best arm identification in multi-armed bandits","volume-title":"Proc. 23rd Conf. Learn. Theory","author":"Audibert"},{"key":"ref6","first-page":"397","article-title":"Using confidence bounds for exploitation-exploration trade-offs","volume":"3","author":"Auer","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref8","first-page":"672","article-title":"General game learning using knowledge transfer","volume-title":"Proc. 20th Int. Joint Conf. Artif. Intell.","author":"Banerjee"},{"issue":"4","key":"ref9","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1080\/00029890.2000.12005203","article-title":"A better bound on the variance","volume":"107","author":"Bhatia","year":"2000","journal-title":"Amer. Math. Monthly"},{"issue":"1","key":"ref10","first-page":"122","article-title":"Matching games and algorithms for general video game playing","volume-title":"Proc. AAAI Conf. Artif. Intell. Interact. Digit. Entertainment","volume":"12","author":"Bontrager"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1009213286"},{"key":"ref12","first-page":"258","article-title":"Multiple identifications in multi-armed bandits","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","volume":"28","author":"Bubeck"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1214\/13-aos1119"},{"issue":"4","key":"ref14","doi-asserted-by":"crossref","first-page":"404","DOI":"10.1093\/biomet\/26.4.404","article-title":"The use of confidence or fiducial limits illustrated in the case of the binomial","volume":"26","author":"Clopper","year":"1934","journal-title":"Biometrika"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967348"},{"key":"ref16","volume-title":"Deep thought (HPC)","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2015.7317937"},{"key":"ref18","first-page":"1","article-title":"Multi-bandit best arm identification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Gabillon"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080420"},{"key":"ref20","first-page":"359","article-title":"The KL-UCB algorithm for bounded stochastic bandits and beyond","volume-title":"Proc. 24th Annu. Conf. Learn. Theory","volume":"19","author":"Garivier"},{"issue":"2","key":"ref21","first-page":"62","article-title":"General game playing: Overview of the aaai competition","volume":"26","author":"Genesereth","year":"2005","journal-title":"AI Mag."},{"issue":"2","key":"ref22","first-page":"1701","article-title":"Deep reinforcement learning for general game playing","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"34","author":"Goldwaser"},{"issue":"2","key":"ref23","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1109\/JSAIT.2021.3082028","article-title":"Best-arm identification in correlated multi-armed bandits","volume":"2","author":"Gupta","year":"2021","journal-title":"IEEE J. Sel. Areas Inf. Theory"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671833"},{"key":"ref25","first-page":"365","article-title":"On correlation and budget constraints in model-based bandit optimization with application to automatic machine learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hoffman"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2014.6814096"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.1946.0056"},{"key":"ref28","first-page":"1238","article-title":"Almost optimal exploration in multi-armed bandits","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","volume":"28","author":"Karnin"},{"issue":"3","key":"ref29","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1016\/j.orl.2021.03.011","article-title":"Best arm identification in generalized linear bandits","volume":"49","author":"Kazerouni","year":"2021","journal-title":"Oper. Res. Lett."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860398"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ITW54588.2022.9965908"},{"issue":"1","key":"ref33","first-page":"4335","article-title":"General video game AI: Competition, challenges and opportunities","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"30","author":"Perez-Liebana"},{"key":"ref34","volume-title":"General Video Game Artificial Intelligence","author":"Perez-Liebana","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860430"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9618990"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA200120"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3233\/ICG-230230"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-86585-5_8"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2019.8849327"},{"key":"ref41","first-page":"1","article-title":"From theories to queries: Active learning in practice","volume-title":"Proc. Act. Learn. Experim. Design Workshop Conjunct With AISTATS","volume":"16","author":"Settles"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860448"},{"key":"ref43","first-page":"1","article-title":"Towards a general transfer approach for policy-value networks","volume":"12","author":"Soemers","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref44","first-page":"234","article-title":"Creating a hyper-agent for solving angry birds levels","volume-title":"Proc. AAAI Conf. Artif. Intell. Interact. Digit. Entertainment","author":"Stephenson"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cec48606.2020.9185834"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847949"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619052"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-34017-8_11"},{"key":"ref49","first-page":"1","article-title":"Deep reinforcement learning for general video game AI","volume-title":"Proc. IEEE Conf. Comput. Intell. Games (CIG)","author":"Torrado"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860383"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1080\/09296174.2013.799918"},{"issue":"1","key":"ref53","first-page":"306","article-title":"Bandit-based planning and learning in continuous-action Markov decision processes","volume-title":"Proc. Int. Conf. Automated Planning Scheduling","volume":"22","author":"Weinstein"},{"issue":"158","key":"ref54","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/01621459.1927.10502953","article-title":"Probable inference, the law of succession, and statistical inference","volume":"22","author":"Wilson","year":"1927","journal-title":"J. Amer. Stat. Assoc."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11488204.pdf?arnumber=11488204","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T19:50:57Z","timestamp":1777319457000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11488204\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3685576","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}