Abstract
This paper investigates a new class of parameterized hybrid genetic algorithms called LV(k) that learns to play Blackjack not only successfully and in some cases, unconventionally, compared to the professional Basic Strategy. For the most promising k class, namely, k=1, we show that 19 instances of these new strategies consistently exceeds previous A.I. efforts by as much as sixteen-fold in game returns. Furthermore, LV(1) is more robust than the Basic Strategy under additive spectral noise by about 1 db at the “flutter” boundary of about –16 db noise intensity where all strategies appear to exhibit statistically significant distortion.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baldwin, R., et al.: The Optimum Strategy in Blackjack. J. Amer Stat. Assoc. (1956)
Braun, J.: The Development and Analysis of Winning Strategies for Casino Blackjack, IBM private report (1977)
Caverlee, J.B.: A Genetic Algorithm Approach to Discovering an Optimal Blackjack Strategy. In: Koza, J. (ed.) Genetic Algorithms and Genetic Programming at Standford (2000)
Fu, K.S.: Syntactic Pattern Recognition and Applications. Prentice-Hall, Englewood Cliffs (1982)
Goldberg, D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley, Reading (1989)
Griffin, P.: The Theory of Blackjack. Huntington (1999)
Pressing, J.: Sources for 1/f noise effects in human cognition and performance. In: Proc. 4th Conf. of the Australasian Cognitive Science Society, Newcastle (1999)
Schroeder, M.: Fractals, Chaos, Power Laws. Freeman, New York (1991)
Simon, J.L.: Resampling: The New Statistics, Resampling Stats Inc. (1995)
Russell, S., Norvig, P.: Artificial Intelligence, 2nd edn. Prentice-Hall, Englewood Cliffs (2003)
Thorp. E.O.: Beat the Dealer (1966)
Wong, S.: Basic Blackjack. Pi Yee (1992)
Yun, Y.: Finding an Optimal Blackjack Strategy using Genetic Algorithms. In: Koza, J. (ed.) Genetic Algorithms and Genetic Programming at Standford (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Coleman, R., Johnson, M.A. (2004). Genetic Algorithm-Induced Optimal Blackjack Strategies in Noisy Settings. In: Tawfik, A.Y., Goodwin, S.D. (eds) Advances in Artificial Intelligence. Canadian AI 2004. Lecture Notes in Computer Science(), vol 3060. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24840-8_39
Download citation
DOI: https://doi.org/10.1007/978-3-540-24840-8_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22004-6
Online ISBN: 978-3-540-24840-8
eBook Packages: Springer Book Archive