{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T14:26:12Z","timestamp":1768919172645,"version":"3.49.0"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2016,7,4]],"date-time":"2016-07-04T00:00:00Z","timestamp":1467590400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2016,7,4]],"date-time":"2016-07-04T00:00:00Z","timestamp":1467590400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["0954116"],"award-info":[{"award-number":["0954116"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Dyn Games Appl"],"published-print":{"date-parts":[[2017,9]]},"DOI":"10.1007\/s13235-016-0198-y","type":"journal-article","created":{"date-parts":[[2016,7,4]],"date-time":"2016-07-04T07:49:48Z","timestamp":1467618588000},"page":"422-442","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Approachability in Stackelberg Stochastic Games with Vector Costs"],"prefix":"10.1007","volume":"7","author":[{"given":"Dileep","family":"Kalathil","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vivek S.","family":"Borkar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rahul","family":"Jain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,7,4]]},"reference":[{"issue":"3","key":"198_CR1","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1137\/S0363012999361974","volume":"40","author":"J Abounadi","year":"2001","unstructured":"Abounadi J, Bertsekas D, Borkar VS (2001) Learning algorithms for Markov decision processes with average cost. SIAM J Control Optim 40(3):681\u2013698","journal-title":"SIAM J Control Optim"},{"key":"198_CR2","volume-title":"Constrained Markov decision processes","author":"E Altman","year":"1999","unstructured":"Altman E (1999) Constrained Markov decision processes, vol 7. CRC Press, Boca Raton"},{"key":"198_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-69512-4","volume-title":"Differential inclusions: set-valued maps and viability theory","author":"JP Aubin","year":"1984","unstructured":"Aubin JP, Cellina A (1984) Differential inclusions: set-valued maps and viability theory. Springer, New York"},{"key":"198_CR4","volume-title":"Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations","author":"M Bardi","year":"2008","unstructured":"Bardi M, Capuzzo-Dolcetta I (2008) Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations. Springer, Berlin"},{"key":"198_CR5","unstructured":"Barwell AD (2011) Omega-limit sets of discrete dynamical systems. Ph.D. dissertation, University of Birmingham"},{"issue":"1","key":"198_CR6","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1137\/S0363012904439301","volume":"44","author":"M Benaim","year":"2005","unstructured":"Benaim M, Hofbauer J, Sorin S (2005) Stochastic approximations and differential inclusions. SIAM J Control Optim 44(1):328\u2013348","journal-title":"SIAM J Control Optim"},{"issue":"4","key":"198_CR7","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1287\/moor.1060.0213","volume":"31","author":"M Benaim","year":"2006","unstructured":"Benaim M, Hofbauer J, Sorin S (2006) Stochastic approximations and differential inclusions, part ii: applications. Math Oper Res 31(4):673\u2013695","journal-title":"Math Oper Res"},{"issue":"1","key":"198_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2140\/pjm.1956.6.1","volume":"6","author":"D Blackwell","year":"1956","unstructured":"Blackwell D (1956) An analog of the minimax theorem for vector payoffs. Pac J Math 6(1):1\u20138","journal-title":"Pac J Math"},{"key":"198_CR9","volume-title":"Topics in controlled Markov chains","author":"VS Borkar","year":"1991","unstructured":"Borkar VS (1991) Topics in controlled Markov chains. Longman Scientific & Technical, Harlow"},{"issue":"3","key":"198_CR10","doi-asserted-by":"publisher","first-page":"840","DOI":"10.1137\/S0363012995282784","volume":"36","author":"VS Borkar","year":"1998","unstructured":"Borkar VS (1998) Asynchronous stochastic approximation. SIAM J Control and Optim 36(3):840\u2013851","journal-title":"SIAM J Control and Optim"},{"issue":"3","key":"198_CR11","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/j.sysconle.2004.08.007","volume":"54","author":"VS Borkar","year":"2005","unstructured":"Borkar VS (2005) An actor-critic algorithm for constrained Markov decision processes. Syst Control Lett 54(3):207\u2013213","journal-title":"Syst Control Lett"},{"key":"198_CR12","doi-asserted-by":"crossref","DOI":"10.1007\/978-93-86279-38-5","volume-title":"Stochastic approximation: a dynamical systems viewpoint","author":"VS Borkar","year":"2008","unstructured":"Borkar VS (2008) Stochastic approximation: a dynamical systems viewpoint. Hindustan Publ Agency, New Delhi, Cambridge University Press, Cambridge"},{"issue":"2","key":"198_CR13","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1137\/S0363012997331639","volume":"38","author":"VS Borkar","year":"2000","unstructured":"Borkar VS, Meyn SP (2000) The ode method for convergence of stochastic approximation and reinforcement learning. SIAM J Control and Optim 38(2):447\u2013469","journal-title":"SIAM J Control and Optim"},{"issue":"3","key":"198_CR14","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1287\/moor.1090.0396","volume":"34","author":"E Even-Dar","year":"2009","unstructured":"Even-Dar E, Kakade S, Mansour Y (2009) Online Markov decision processes. Math Oper Res 34(3):726\u2013736","journal-title":"Math Oper Res"},{"key":"198_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9","volume-title":"Competitive Markov decision processes","author":"J Filar","year":"1996","unstructured":"Filar J, Vrieze K (1996) Competitive Markov decision processes. Springer, New York"},{"key":"198_CR16","unstructured":"Kamal S (2010) A vector minmax problem for controlled Markov chains. Arxiv preprint, \n                    arXiv:1011.0675v1"},{"issue":"2","key":"198_CR17","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1287\/moor.28.2.327.14483","volume":"28","author":"S Mannor","year":"2003","unstructured":"Mannor S, Shimkin N (2003) The empirical Bayes envelope and regret minimization in competitive Markov decision processes. Math Oper Res 28(2):327\u2013345","journal-title":"Math Oper Res"},{"key":"198_CR18","first-page":"325","volume":"5","author":"S Mannor","year":"2004","unstructured":"Mannor S, Shimkin N (2004) A geometric approach to multi-criterion reinforcement learning. J Mach Learn Res 5:325\u2013360","journal-title":"J Mach Learn Res"},{"issue":"1","key":"198_CR19","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.geb.2005.06.005","volume":"56","author":"E Milman","year":"2006","unstructured":"Milman E (2006) Approachable sets of vector payoffs in stochastic games. Games Econom Behav 56(1):135\u2013147","journal-title":"Games Econom Behav"},{"key":"198_CR20","unstructured":"Patek SD (1997) Stochastic shortest path games: theory and algorithms. Ph.D. dissertation, Lab. for Information and Decision Systems, MIT"},{"issue":"2","key":"198_CR21","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3934\/jdg.2014.1.181","volume":"1","author":"V Perchet","year":"2014","unstructured":"Perchet V (2014) Approachability, regret and calibration; implications and equivalences. J Dyn Games 1(2):181\u2013254","journal-title":"J Dyn Games"},{"key":"198_CR22","volume-title":"Markov decision processes: discrete stochastic dynamic programming","author":"ML Puterman","year":"2014","unstructured":"Puterman ML (2014) Markov decision processes: discrete stochastic dynamic programming. Wiley, New York"},{"issue":"1","key":"198_CR23","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/9.186314","volume":"38","author":"N Shimkin","year":"1993","unstructured":"Shimkin N, Shwartz A (1993) Guaranteed performance regions in Markovian systems with competing decision makers. IEEE Trans Autom Control 38(1):84\u201395","journal-title":"IEEE Trans Autom Control"},{"key":"198_CR24","volume-title":"Multiple criteria optimization: theory, computation, and application","author":"RE Steuer","year":"1989","unstructured":"Steuer RE (1989) Multiple criteria optimization: theory, computation, and application. Wiley, New York"},{"issue":"12","key":"198_CR25","first-page":"1197","volume":"328","author":"W Tucker","year":"1999","unstructured":"Tucker W (1999) The Lorenz attractor exists. Comptes Rendus Acad Sci Ser I Math 328(12):1197\u20131202","journal-title":"Comptes Rendus Acad Sci Ser I Math"},{"issue":"5","key":"198_CR26","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1137\/0315056","volume":"15","author":"DH Wagner","year":"1977","unstructured":"Wagner DH (1977) Survey of measurable selection theorems. SIAM J Control and Optim 15(5):859\u2013903","journal-title":"SIAM J Control and Optim"},{"issue":"3","key":"198_CR27","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1287\/moor.1090.0397","volume":"34","author":"JY Yu","year":"2009","unstructured":"Yu JY, Mannor S, Shimkin N (2009) Markov decision processes with arbitrary reward processes. Math Oper Res 34(3):737\u2013757","journal-title":"Math Oper Res"},{"issue":"2","key":"198_CR28","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1287\/moor.1120.0562","volume":"38","author":"H Yu","year":"2013","unstructured":"Yu H, Bertsekas DP (2013) On boundedness of Q-learning iterates for stochastic shortest path problems. Math Oper Res 38(2):209\u2013227","journal-title":"Math Oper Res"}],"container-title":["Dynamic Games and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s13235-016-0198-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-016-0198-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-016-0198-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s13235-016-0198-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,17]],"date-time":"2020-05-17T18:26:13Z","timestamp":1589739973000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s13235-016-0198-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,4]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,9]]}},"alternative-id":["198"],"URL":"https:\/\/doi.org\/10.1007\/s13235-016-0198-y","relation":{},"ISSN":["2153-0785","2153-0793"],"issn-type":[{"value":"2153-0785","type":"print"},{"value":"2153-0793","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7,4]]},"assertion":[{"value":"4 July 2016","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}