Genetic Algorithm-Induced Optimal Blackjack Strategies in Noisy Settings

@inproceedings{Coleman2004GeneticAO,
  title={Genetic Algorithm-Induced Optimal Blackjack Strategies in Noisy Settings},
  author={Ron Coleman and Matthew A. Johnson},
  booktitle={Canadian Conference on AI},
  year={2004}
}
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… CONTINUE READING

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-2 OF 2 CITATIONS

Boosting Blackjack Returns with Machine Learned Betting Criteria

  • Third International Conference on Information Technology: New Generations (ITNG'06)
  • 2006
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND