{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T22:21:08Z","timestamp":1725488468241},"publisher-location":"Berlin, Heidelberg","reference-count":22,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540423430"},{"type":"electronic","value":"9783540445814"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2001]]},"DOI":"10.1007\/3-540-44581-1_9","type":"book-chapter","created":{"date-parts":[[2007,8,10]],"date-time":"2007-08-10T06:13:49Z","timestamp":1186726429000},"page":"128-142","source":"Crossref","is-referenced-by-count":1,"title":["Adaptive Strategies and Regret Minimization in Arbitrarily Varying Markov Environments"],"prefix":"10.1007","author":[{"given":"Shie","family":"Mannor","sequence":"first","affiliation":[]},{"given":"Nahum","family":"Shimkin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2001,9,13]]},"reference":[{"key":"9_CR1","unstructured":"Special issue on learning in games. Games and Economic Behavior, 29(1), November 1999."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"P. Auer, N. Cesa-Bianchi, Y. Freund, and R.E. Schapire. Gambling in a rigged casino: The adversarial multi armed bandit problem. In Proc. 36th Annual Symposium on Foundations of Computer Science, pages 322\u2013331. IEEE Computer Society Press, 1995.","DOI":"10.1109\/SFCS.1995.492488"},{"key":"9_CR3","unstructured":"D.P. Bertsekas and J.N. Tsitsiklis. Neuro-Dynamic Programming. Athena Scientific, 1995."},{"issue":"1","key":"9_CR4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2140\/pjm.1956.6.1","volume":"6","author":"D. Blackwell","year":"1956","unstructured":"D. Blackwell. An analog of the minimax theorem for vector payoffs. Pacific J. Math., 6(1):1\u20138, 1956.","journal-title":"Pacific J. Math."},{"key":"9_CR5","first-page":"336","volume":"III","author":"D. Blackwell","year":"1954","unstructured":"D. Blackwell. Controlled random walks. In Proc. International Congress of Mathematicians, 1954, volume III, pages 336\u2013338. North-Holland, 1956.","journal-title":"Proc. International Congress of Mathematicians"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"J. Filar and K. Vrieze. Competitive Markov Decision Processes. Springer Verlag, 1996.","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"9_CR7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1006\/game.1999.0738","volume":"29","author":"Y. Freund","year":"1999","unstructured":"Y. Freund and R. Schapire. Adaptive game playing using multiplicative weights. Games and Economic Behavior, 29:79\u2013103, November 1999.","journal-title":"Games and Economic Behavior"},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1016\/0165-1889(94)00819-4","volume":"19","author":"D. Fudenberg","year":"1995","unstructured":"D. Fudenberg and D. Levine. Universal consistency and cautious fictitious play. Journal of Economic Dynamic and Control, 19:1065\u20131990, 1995.","journal-title":"Journal of Economic Dynamic and Control"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"J. Hannan. Approximation to bayes risk in repeated play. In M. Dresher, A.W. Tucker, and P. Wolde, editors, Contribution to The Theory of Games, III, pages 97\u2013139. Princeton University Press, 1957.","DOI":"10.1515\/9781400882151-006"},{"key":"9_CR10","unstructured":"S. Hart and A. Mas-Colell. A simple adaptive procedure leading to correlated equilibrium. DP 166, The Hebrew University of Jerusalem, Center for Rationality, 1998."},{"key":"9_CR11","unstructured":"E. Lehrer. Approachability in infinite dimensional spaces and an application: A universal algorithm for generating extended normal numbers. Preprint, May 1998."},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"M.L. Littman. Markov games as a framework for multi-agent reinforcement learning. In Morgan Kaufman, editor, Eleventh International Conference on Machine Learning, pages 157\u2013163, 1994.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"9_CR13","unstructured":"S. Mannor and N. Shimkin. The empirical bayes envelope approach to regret minimization in stochastic games. Technical report EE-1262, Faculty of Electrical Engineering, Technion, Israel, October 2000. available from: http:\/\/tiger.technion.ac.il\/~shie\/Public\/drmOct23techreport.ps.gz ."},{"key":"9_CR14","unstructured":"S. Mannor and N. Shimkin. Regret minimization in signal space for repeated matrix games with partial observations. Technical report EE-1242, Faculty of Electrical Engineering, Technion, Israel, March 2000. available from: http:\/\/tiger.technion.ac.il\/~shie\/Public\/beMar16.ps.gz ."},{"key":"9_CR15","unstructured":"T. Parthasarathy and M. Stern. Markov games-a survey. Differential Games and Control Theory, 1977."},{"key":"9_CR16","unstructured":"S.D. Patek. Stochastic Shortest Path Games. PhD thesis, LIDS MIT, January 1997."},{"key":"9_CR17","doi-asserted-by":"crossref","unstructured":"M. Puterman. Markov Decision Processes. Wiley-Interscience, 1994.","DOI":"10.1002\/9780470316887"},{"key":"9_CR18","unstructured":"E. Rasmunsen. Games and Information: An Introduction to Game Theory. Blackwell, 1994."},{"key":"9_CR19","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1006\/game.1998.0690","volume":"29","author":"A. Rustichini","year":"1999","unstructured":"A. Rustichini. Minimizing regret: the general case. Games and Economic Behavior, 29:224\u2013243, November 1999.","journal-title":"Games and Economic Behavior"},{"issue":"1","key":"9_CR20","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/9.186314","volume":"38","author":"N. Shimkin","year":"1993","unstructured":"N. Shimkin and A. Shwartz. Guaranteed performance regions in markovian systems with competing decision makers. IEEE Trans. on Automatic Control, 38(1):84\u201395, January 1993.","journal-title":"IEEE Trans. on Automatic Control"},{"key":"9_CR21","unstructured":"X. Spiant. An approachability condition for general sets. Technical Report 496, Ecole Polytechnique, Paris, 1999."},{"issue":"2","key":"9_CR22","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1006\/jcss.1997.1556","volume":"56","author":"V. Vovk","year":"1998","unstructured":"V. Vovk. A game of prediction with experts advice. Journal of Computer and Systems Sciences, 56(2):153\u2013173, April 1998.","journal-title":"Journal of Computer and Systems Sciences"}],"container-title":["Lecture Notes in Computer Science","Computational Learning Theory"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-44581-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,25]],"date-time":"2020-04-25T15:32:41Z","timestamp":1587828761000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-44581-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001]]},"ISBN":["9783540423430","9783540445814"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/3-540-44581-1_9","relation":{},"ISSN":["0302-9743"],"issn-type":[{"type":"print","value":"0302-9743"}],"subject":[],"published":{"date-parts":[[2001]]}}}