{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T12:10:02Z","timestamp":1752149402385,"version":"3.41.2"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2002,10,1]],"date-time":"2002-10-01T00:00:00Z","timestamp":1033430400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2002,10,1]],"date-time":"2002-10-01T00:00:00Z","timestamp":1033430400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[2002,10]]},"DOI":"10.1023\/a:1014063505958","type":"journal-article","created":{"date-parts":[[2002,12,28]],"date-time":"2002-12-28T14:42:56Z","timestamp":1041086576000},"page":"5-37","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["The Lagging Anchor Algorithm: Reinforcement Learning in Two-Player Zero-Sum Games with Imperfect Information"],"prefix":"10.1007","volume":"49","author":[{"given":"Fredrik A.","family":"Dahl","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"394118_CR1","first-page":"263","volume-title":"Proceedings of the Seventh Conference on Computer Generated Forces and Behavioral Representation","author":"B. T. Bakken","year":"1998","unstructured":"Bakken, B. T., & Dahl, F. A. (1998). Experimental studies of neural net training and human learning in a military air campaign game. Proceedings of the Seventh Conference on Computer Generated Forces and Behavioral Representation, University of Central Florida, Orlando, Florida, Institute for Simulation and Training, pp. 263-274."},{"key":"394118_CR2","doi-asserted-by":"crossref","unstructured":"Berkovitz, L. D. (1975). The tactical air game: A multimove game with mixed strategy solution. In J. D. Grote (Ed.), The theory and application of differential games (pp. 169-177).","DOI":"10.1007\/978-94-010-1804-3_15"},{"key":"394118_CR3","series-title":"Interscience tracts in pure and applied mathematics, No.","volume-title":"Convex surfaces","author":"H. Busemann","year":"1958","unstructured":"Busemann, H. (1958). Convex surfaces. Interscience tracts in pure and applied mathematics, No. 6. New York: Interscience Publishers."},{"key":"394118_CR4","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/0167-2681(93)90071-V","volume":"22","author":"J. Conlisk","year":"1993","unstructured":"Conlisk, J. (1993a). Adaptation in games-2 solutions to the Crawford puzzle. Journal of Economic Behavior and Organizations, 22, 25-50.","journal-title":"Journal of Economic Behavior and Organizations"},{"key":"394118_CR5","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/0167-2681(93)90072-W","volume":"22","author":"J. Conlisk","year":"1993","unstructured":"Conlisk, J. (1993b). Adaptive tactics in games-Further solutions to the Crawford puzzle. Journal of EconomicBehavior and Organizations, 22, 51-68.","journal-title":"Journal of EconomicBehavior and Organizations"},{"key":"394118_CR6","doi-asserted-by":"crossref","first-page":"885","DOI":"10.2307\/1913795","volume":"42","author":"V. P. Crawford","year":"1974","unstructured":"Crawford, V. P. (1974). Learning the optimal strategy in a zero-sum game. Econometrica, 42, 885-891.","journal-title":"Econometrica"},{"key":"394118_CR7","series-title":"FFI\/Rapport-98\/02799","volume-title":"Definitions and properties of the games campaign, Operation lucid and operation opaque","author":"F. A. Dahl","year":"1998","unstructured":"Dahl, F. A., & Halck, O. M. (1998). Three games designed for the study of human and automated decision making. Definitions and properties of the games campaign, Operation lucid and operation opaque. FFI\/Rapport-98\/02799, Norwegian Defence Research Establishment (FFI), Kjeller, Norway."},{"key":"394118_CR8","series-title":"Lecture Notes in Computer Science","volume-title":"ECML 2000. Proceedings of the 11th European Conference on Machine Learning","author":"F. A. Dahl","year":"2000","unstructured":"Dahl, F. A., & Halck, O. M. (2000). Minimax TD-learning with neural nets in a Markov game. In R. Lopez de Mantaras & E. Plaza (Eds.), ECML 2000. Proceedings of the 11th European Conference on Machine Learning, Lecture Notes in Computer Science (Vol. 1810). Berlin: Springer-Verlag."},{"key":"394118_CR9","series-title":"FFI\/Rapport-2000\/04400","volume-title":"Machine learning in the game of Campaign","author":"F. A. Dahl","year":"2000","unstructured":"Dahl, F. A., Halck, O. M., & Braathen, S. (2000). Machine learning in the game of Campaign. FFI\/Rapport-2000\/04400, Norwegian Defence Research Establishment (FFI), Kjeller, Norway."},{"key":"394118_CR10","first-page":"848","volume":"88","author":"I. Erev","year":"1998","unstructured":"Erev, I., & Roth, A. E. (1998). Predicting how people play games: Reinforcement learning in experimental games with unique, mixed strategy equilibria. The American economic review, 88, 848-881.","journal-title":"The American economic review"},{"key":"394118_CR11","volume-title":"The theory of learning in games","author":"D. Fudenberg","year":"1998","unstructured":"Fudenberg, D., & Levine, D. K. (1998). The theory of learning in games. Cambridge: MIT Press."},{"key":"394118_CR12","volume-title":"Proceedings of the ICML-99Workshop on Machine Learning in Game Playing","author":"O. M. Halck","year":"1999","unstructured":"Halck, O. M., & Dahl, F. A. (1999). On classification of games and evaluation of players-with some sweeping generalizations about the literature. In: J. F\u00fcrnkranz,& M. Kubat (Eds.), Proceedings of the ICML-99Workshop on Machine Learning in Game Playing. Ljubljana, Slovenia: Jozef Stefan Institute."},{"key":"394118_CR13","volume-title":"Adaptive behavior (Vol. 0004)","author":"M. E. Harmon","year":"1995","unstructured":"Harmon, M. E., Baird, L. C., & Klopf, A. H. (1995). Reinforcement learning applied to a differential game. Adaptive behavior (Vol. 0004). Cambridge, MA: MIT Press."},{"key":"394118_CR14","volume-title":"Fundamentals of artificial neural networks","author":"M. H. Hassoun","year":"1995","unstructured":"Hassoun, M. H. (1995). Fundamentals of artificial neural networks. Cambridge, MA: MIT Press."},{"key":"394118_CR15","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1006\/game.1996.0051","volume":"14","author":"D. Koller","year":"1996","unstructured":"Koller, D., Megiddo, N., & von Stengel, B. (1996). Efficient solutions of extensive two-person games. Games and Economic Behavior, 14, 247-259.","journal-title":"Games and Economic Behavior"},{"key":"394118_CR16","first-page":"157","volume-title":"Proceedings of the 11th International Conference on Machine Learning","author":"M. L. Littman","year":"1994","unstructured":"Littman, M. L. (1994). Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the 11th International Conference on Machine Learning (pp. 157-163). New Brunswick: Morgan Kaufmann."},{"key":"394118_CR17","volume-title":"Games and decisions","author":"R. D. Luce","year":"1957","unstructured":"Luce, R. D., & Raiffa, H. (1957). Games and decisions. New York: Wiley."},{"key":"394118_CR18","volume-title":"Introduction to dynamic systems. Theory, models, & applications","author":"D. G. Luenberger","year":"1979","unstructured":"Luenberger D. G. (1979). Introduction to dynamic systems. Theory, models, & applications. New York: Wiley."},{"key":"394118_CR19","volume-title":"Linear and nonlinear programming","author":"D. G. Luenberger","year":"1984","unstructured":"Luenberger, D. G. (1984). Linear and nonlinear programming. Reading, MA: Addison-Wesley."},{"key":"394118_CR20","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/B978-0-08-011356-2.50011-2","volume-title":"Advances in programming and non-numerical computation","author":"D. Michie","year":"1966","unstructured":"Michie, D. (1966). Game-playing and game-learning automata. In L. Fox (Ed.), Advances in programming and non-numerical computation (pp. 183-200). New York, Pergamon."},{"key":"394118_CR21","volume-title":"Linear optimization and extensions","author":"M. Padberg","year":"1995","unstructured":"Padberg, M. (1995). Linear optimization and extensions. Berlin: Springer-Verlag."},{"key":"394118_CR22","volume-title":"Computational complexity","author":"C. H. Papadimitriou","year":"1994","unstructured":"Papadimitriou, C. H. (1994). Computational complexity. Reading, MA: Addison Wesley."},{"key":"394118_CR23","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1147\/rd.33.0210","volume":"3","author":"A. L. Samuel","year":"1959","unstructured":"Samuel, A. L. (1959). Some studies in machine learning using the game of checkers. IBM J Res. Develop., 3, 210-229.","journal-title":"IBM J Res. Develop."},{"key":"394118_CR24","volume-title":"Proceedings of the ICML-99 Workshop on Machine Learning in Game Playing","author":"J. Schaeffer","year":"1999","unstructured":"Schaeffer, J., Billings, D., Pe\u00f1a, L., & Szafron, D. (1999). Learning to play strong poker. In: J. Furnkranz, & M. Kubat (Eds.), Proceedings of the ICML-99 Workshop on Machine Learning in Game Playing, Ljubljana, Slovenia: Jozef Stefan Institute."},{"key":"394118_CR25","volume-title":"Game equilibrium models (Vol. I: Evolution and game dynamics)","author":"R. Selten","year":"1991","unstructured":"Selten, R. (1991). Anticipatory learning in two-person games. In R. Selten (Ed.), Game equilibrium models (Vol. I: Evolution and game dynamics). Berlin: Springer-Verlag."},{"key":"394118_CR26","volume-title":"Linear algebra and its applications","author":"G. Strang","year":"1980","unstructured":"Strang, G. (1980). Linear algebra and its applications. London: Harcourt Brace."},{"key":"394118_CR27","first-page":"9","volume":"3","author":"R. S. Sutton","year":"1988","unstructured":"Sutton, R. S. (1988). Learning to predict by the methods of temporal differences. Machine Learning, 3, 9-44.","journal-title":"Machine Learning"},{"key":"394118_CR28","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1162\/089976699300016070","volume":"11","author":"C. Szepesvari","year":"1999","unstructured":"Szepesvari, C., & Littman, M. L. (1999). A unified analysis of value-function-based reinforcement-learning algorithms. Neural Computation, 11, 2017-2060.","journal-title":"Neural Computation"},{"key":"394118_CR29","first-page":"257","volume":"8","author":"G. J. Tesauro","year":"1992","unstructured":"Tesauro, G. J. (1992). Practical issues in temporal difference learning. Machine Learning, 8, 257-277.","journal-title":"Machine Learning"},{"key":"394118_CR30","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1016\/0004-3702(89)90017-9","volume":"39","author":"G. J. Tesauro","year":"1989","unstructured":"Tesauro, G. J., & Sejnowski, T. J. (1989).Aparallel network that learns to play backgammon. Artificial Intelligence, 39, 357-390.","journal-title":"Artificial Intelligence"},{"key":"394118_CR31","volume-title":"Theory of games and economic behavior","author":"J. von Neumann","year":"1953","unstructured":"von Neumann, J., & Morgenstern, O. (1953). Theory of games and economic behavior, 3rd ed. New York: Wiley.","edition":"3rd ed."},{"key":"394118_CR32","volume-title":"Learning from delayed rewards","author":"C. J. C. H. Watkins","year":"1989","unstructured":"Watkins, C. J. C. H. (1989). Learning from delayed rewards. PhD thesis, Psychology Department, Cambridge University, Cambridge, UK."},{"key":"394118_CR33","volume-title":"Evolutionary game theory","author":"J. Weibull","year":"1995","unstructured":"Weibull, J. (1995). Evolutionary game theory, Cambridge: MIT Press."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1014063505958.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1014063505958\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1014063505958.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:36:40Z","timestamp":1752147400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1014063505958"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2002,10]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2002,10]]}},"alternative-id":["394118"],"URL":"https:\/\/doi.org\/10.1023\/a:1014063505958","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2002,10]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}