{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T06:10:04Z","timestamp":1766297404518,"version":"3.48.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100802"],"award-info":[{"award-number":["2018AAA0100802"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tg.2025.3579719","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T15:02:21Z","timestamp":1750086141000},"page":"975-988","source":"Crossref","is-referenced-by-count":1,"title":["Exp3.P-Based Autonomous Decision Algorithm Against Nonstationary Opponents With Partially Known Policies"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6038-4339","authenticated-orcid":false,"given":"Jin","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhui","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6405-7753","authenticated-orcid":false,"given":"Jiacheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0596-6050","authenticated-orcid":false,"given":"Geir E.","family":"Dullerud","sequence":"additional","affiliation":[{"name":"Department of Mechanical Science and Engineering, University of Illinois at Urbana–Champaign, Urbana, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"PokerGPT: An end-to-end lightweight solver for multi-player Texas Holdem via large language model","year":"2024","author":"Huang","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1426-8"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3296769"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3259724"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2024.3372939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2024.3404133"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-016-9352-6"},{"key":"ref8","first-page":"1315","article-title":"A Bayesian approach for learning and tracking switching, non-stationary opponents","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Hernandez-Leal","year":"2016"},{"key":"ref9","first-page":"25502","article-title":"Why generalization in RL is difficult: Epistemic POMDPs and implicit partial observability","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Ghosh","year":"2021"},{"key":"ref10","first-page":"1","article-title":"Discovering generalizable multi-agent coordination skills from multi-task offline data","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang","year":"2022"},{"article-title":"A survey of learning in multiagent environments: Dealing with non-stationarity","year":"2017","author":"Hernandez-Leal","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3347-8"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06344-1"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1515\/9781400881727-010"},{"key":"ref15","first-page":"4940","article-title":"Prioritized level replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref17","first-page":"19210","article-title":"Agent modelling under partial observability for deep reinforcement learning","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","author":"Papoudakis","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref19","first-page":"1804","article-title":"Opponent modeling in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"He","year":"2016"},{"article-title":"A deep policy inference Q-network for multi-agent systems","year":"2017","author":"Hong","key":"ref20"},{"key":"ref21","first-page":"602","article-title":"A regularized opponent model with maximum entropy objective [J\/OL]","volume":"1","author":"Zheng","year":"2022","journal-title":"Proc.28th Int. Joint Conf. Artif. Intell."},{"key":"ref22","first-page":"506","article-title":"Best-response multiagent learning in non-stationary environments","volume-title":"Proc. 3rd Int. Joint Conf. Auton. Agents Multiagent Syst.","author":"Weinberg","year":"2004"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24412-4_16"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/88"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.108715"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2013.2253094"},{"key":"ref27","first-page":"213","article-title":"R-max-a general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"Brafman","year":"2002","journal-title":"J. Mach. Learn. Res."},{"key":"ref28","first-page":"780","article-title":"Predicting and preventing coordination problems in cooperative Q-learning systems","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","volume":"2007","author":"Fulda","year":"2007"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5547-y"},{"key":"ref30","first-page":"962","article-title":"A deep Bayesian policy reuse approach against non-stationary agents","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Zheng","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_2"},{"key":"ref32","first-page":"4257","article-title":"Modeling others using oneself in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Raileanu","year":"2018"},{"key":"ref33","first-page":"28208","article-title":"Model-based opponent modeling","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"article-title":"Variational autoencoders for opponent modeling in multi-agent systems","year":"2020","author":"Papoudakis","key":"ref34"},{"key":"ref35","first-page":"3309","article-title":"Equivariant reinforcement learning under partial observability","volume-title":"Proc. Conf. Robot Learn.","author":"Nguyen","year":"2023"},{"article-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref36"},{"issue":"137","key":"ref37","first-page":"1","article-title":"A survey on multi-player bandits","volume":"25","author":"Boursier","year":"2024","journal-title":"J. Mach. Learn. Res."},{"article-title":"A bandit framework for optimal selection of reinforcement learning agents","year":"2019","author":"Merentitis","key":"ref38"},{"key":"ref39","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia","year":"2020"},{"key":"ref40","first-page":"6948","article-title":"Reinforcement learning can be more efficient with multiple rewards","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dann","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-35883-8_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.2307\/2332286"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2022.2136727"},{"article-title":"Multi-agent reinforcement learning: A comprehensive survey","year":"2023","author":"Huh","key":"ref45"},{"key":"ref46","first-page":"4218","article-title":"Machine theory of mind","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rabinowitz","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3302694"},{"key":"ref48","first-page":"5081","article-title":"Decision-making with auto-encoding variational Bayes","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Lopez","year":"2020"},{"key":"ref49","first-page":"721","article-title":"Computing robust counter-strategies","volume-title":"Proc. 21st Int. Conf. Neural Inf. Process. Syst.","author":"Johanson","year":"2007"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636344"},{"article-title":"Auto-encoding variational Bayes","year":"2013","author":"Kingma","key":"ref51"},{"key":"ref52","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. 19th Int. Conf. Mach. Learn.","author":"Kakade","year":"2002"},{"key":"ref53","first-page":"263","article-title":"Minimax regret bounds for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Azar","year":"2017"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5091-5"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11301972\/11037288.pdf?arnumber=11037288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:35:51Z","timestamp":1766082951000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11037288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":56,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3579719","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}