{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:11:11Z","timestamp":1767183071700,"version":"3.40.5"},"reference-count":58,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM Journal on Mathematics of Data Science"],"published-print":{"date-parts":[[2023,9,30]]},"DOI":"10.1137\/22m1515112","type":"journal-article","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T08:45:09Z","timestamp":1692866709000},"page":"745-773","source":"Crossref","is-referenced-by-count":17,"title":["Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games"],"prefix":"10.1137","volume":"5","author":[{"given":"Bora","family":"Yongacoglu","sequence":"first","affiliation":[{"name":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8295-1509","authenticated-orcid":true,"given":"G\u00fcrdal","family":"Arslan","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, University of Hawaii at Manoa, Honolulu, HI 96822 USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Serdar","family":"Y\u00fcksel","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Queen\u2019s University, Kingston, ON, Canada."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"351","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"ref1","first-page":"1","volume":"22","author":"Agarwal A.","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","doi-asserted-by":"crossref","first-page":"1545","DOI":"10.1109\/TAC.2016.2598476","volume":"62","author":"Arslan G.","year":"2017","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref3","first-page":"2159","volume":"33","author":"Bai Y.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref4","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"Bowling M.","year":"2002","journal-title":"Artif. Intell."},{"key":"ref5","first-page":"374","volume":"13","author":"Brown G. W.","year":"1951","journal-title":"Act. Anal. Prod. Allocation"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1126\/science.aao1733","volume":"359","author":"Brown N.","year":"2018","journal-title":"Science"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2465769.2465776","volume":"1","author":"Candogan O.","year":"2013","journal-title":"ACM Trans. Econ. Comput."},{"key":"ref8","first-page":"3740","volume":"44","author":"Carmona R.","year":"2016","journal-title":"Ann. Probab."},{"key":"ref9","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1287\/mnsc.19.3.266","volume":"19","author":"Cassidy R.","year":"1972","journal-title":"Manag. Sci."},{"key":"ref10","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1287\/opre.11.1.18","volume":"11","author":"Charnes A.","year":"1963","journal-title":"Oper. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1137\/110852462"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1016\/j.geb.2009.05.004","volume":"71","author":"Chien S.","year":"2011","journal-title":"Games Econom. Behav."},{"key":"ref15","first-page":"5527","volume":"33","author":"Daskalakis C.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref17","volume":"30","author":"Devraj A. M.","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref18","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1109\/TAC.2017.2747767","volume":"63","author":"Eksin C.","year":"2017","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref19","first-page":"1","volume":"5","author":"Even-Dar E.","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref20","first-page":"89","volume":"28","author":"Fink A. M.","year":"1964","journal-title":"J. Sci. Hiroshima Univ. Ser. AI Math."},{"key":"ref21","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1214\/16-AAP1215","volume":"27","author":"Fischer M.","year":"2017","journal-title":"Ann. Appl. Probab."},{"key":"ref22","first-page":"341","volume":"1","author":"Foster D.","year":"2006","journal-title":"Theor. Econ."},{"key":"ref23","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1006\/game.1995.1052","volume":"11","author":"Gaunersdorfer A.","year":"1995","journal-title":"Games Econom. Behav."},{"key":"ref24","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.geb.2006.06.001","volume":"60","author":"Germano F.","year":"2007","journal-title":"Games Econom. Behav."},{"volume-title":"Proceedings of Advances in Neural Information Processing Systems","year":"2011","author":"Ghavamzadeh M.","key":"ref25"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"1830","DOI":"10.1257\/000282803322655581","volume":"93","author":"Hart S.","year":"2003","journal-title":"Amer. Econ. Rev."},{"key":"ref27","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.geb.2005.09.007","volume":"57","author":"Hart S.","year":"2006","journal-title":"Games Econom. Behav."},{"key":"ref29","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1090\/S0273-0979-03-00988-1","volume":"40","author":"Hofbauer J.","year":"2003","journal-title":"Bull. Amer. Math. Soc. (N.S.)"},{"key":"ref30","first-page":"1039","volume":"4","author":"Hu J.","year":"2003","journal-title":"J. Mach. Learn. Res."},{"key":"ref31","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1109\/TAC.2007.904450","volume":"52","author":"Huang M.","year":"2007","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"221","DOI":"10.4310\/CIS.2006.v6.n2.a2","volume":"6","author":"Huang M.","year":"2006","journal-title":"Commun. Inf. Syst."},{"key":"ref33","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/s11537-007-0657-8","volume":"2","author":"Lasry J.-M.","year":"2007","journal-title":"Jpn. J. Math."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012903437976"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"105095","DOI":"10.1016\/j.jet.2020.105095","volume":"189","author":"Leslie D. S.","year":"2020","journal-title":"J. Econom. Theory"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"1973","DOI":"10.3982\/ECTA10530","volume":"81","author":"Levy Y.","year":"2013","journal-title":"Econometrica"},{"key":"ref41","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1016\/j.geb.2012.03.006","volume":"75","author":"Marden J. R.","year":"2012","journal-title":"Games Econom. Behav."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1137\/070680199"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/110850694"},{"key":"ref46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1017\/S0269888912000057","volume":"27","author":"Matignon L.","year":"2012","journal-title":"Knowl. Eng. Rev."},{"key":"ref47","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/0022-0531(92)90040-O","volume":"57","author":"Matsui A.","year":"1992","journal-title":"J. Econom. Theory"},{"key":"ref48","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"Mnih V.","year":"2015","journal-title":"Nature"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"296","DOI":"10.2307\/1969530","volume":"54","author":"Robinson J.","year":"1951","journal-title":"Ann. of Math."},{"key":"ref53","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1145\/1785414.1785439","volume":"53","author":"Roughgarden T.","year":"2010","journal-title":"Commun. ACM"},{"journal-title":"Math. Oper. Res.","year":"2022","author":"Sanjari S.","key":"ref54"},{"key":"ref55","doi-asserted-by":"crossref","first-page":"1071","DOI":"10.1109\/TAC.2020.2994899","volume":"66","author":"Sanjari S.","year":"2020","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1137\/19M1284294"},{"key":"ref57","first-page":"18320","volume":"34","author":"Sayin M.","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1137\/21M1426675"},{"journal-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"Schulman J.","key":"ref60"},{"key":"ref62","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"Silver D.","year":"2016","journal-title":"Nature"},{"key":"ref63","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"Silver D.","year":"2017","journal-title":"Nature"},{"key":"ref64","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1037\/h0042769","volume":"63","author":"Simon H. A.","year":"1956","journal-title":"Psychol. Rev."},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton R. S.","key":"ref65"},{"key":"ref66","doi-asserted-by":"crossref","first-page":"4294","DOI":"10.1109\/TAC.2018.2817161","volume":"63","author":"Swenson B.","year":"2018","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref67","volume":"10","author":"Szepesv\u00e1ri C.","year":"1997","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref69","first-page":"185","volume":"16","author":"Tsitsiklis J. N.","year":"1994","journal-title":"Mach. Learn."},{"key":"ref71","first-page":"279","volume":"8","author":"Watkins C.","year":"1992","journal-title":"Mach. Learn."},{"key":"ref72","volume":"30","author":"Wei C.-Y.","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref73","first-page":"2914","volume":"17","author":"Wei E.","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref74","doi-asserted-by":"crossref","first-page":"5230","DOI":"10.1109\/TAC.2021.3121228","volume":"67","author":"Yongacoglu B.","year":"2021","journal-title":"IEEE Trans. Automat. Control"},{"key":"ref77","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1007\/978-3-030-60990-0_12","author":"Zhang K.","year":"2021","journal-title":"Handbook of Reinforcement Learning and Control"}],"container-title":["SIAM Journal on Mathematics of Data Science"],"original-title":[],"language":"en","deposited":{"date-parts":[[2023,9,29]],"date-time":"2023-09-29T15:48:52Z","timestamp":1696002532000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/22M1515112"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,24]]},"references-count":58,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9,30]]}},"alternative-id":["10.1137\/22M1515112"],"URL":"https:\/\/doi.org\/10.1137\/22m1515112","relation":{},"ISSN":["2577-0187"],"issn-type":[{"type":"electronic","value":"2577-0187"}],"subject":[],"published":{"date-parts":[[2023,8,24]]}}}