The discipline of artificial intelligence (AI) is a diverse field, with a vast variety of philosophies and implementations to consider. This work attempts to compare several of these paradigms as well as their variations and hybrids, using the card game of blackjack as the field of competition. This is done with an automated blackjack emulator, written in Java, which accepts computer-controlled players of various AI philosophies and their variants, training them and finally pitting them against each other in a series of tournaments with customizable rule sets. In order to avoid bias towards any particular implementation, the system treats each group as a team, allowing each team to run optimally and handle their own evolution. The primary AI paradigms examined in this work are rule-based AI and genetic learning, drawing from the philosophies of fuzzy logic and intelligent agents. The rule-based AI teams apply various commonly used algorithms for real-world blackjack, ranging from the basic rules of a dealer to the situational "rule of thumb" formula suggested to amateurs. The blackjack options of hit, stand, surrender, and double down are supported, but advanced options such as hand splitting and card counting are not examined. Various tests exploring possible configurations of genetic learning systems were devised, implemented, and analyzed. Future work would expand the variety and complexity of the teams, as well as implementing advanced game features.


Rebecca Bates

Committee Member

Dean Kelley

Committee Member

Christophe Veltsos

Date of Degree




Document Type



Master of Science (MS)


Computer Information Science


Science, Engineering and Technology

Creative Commons License

Creative Commons Attribution-NonCommercial 4.0 International License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License



Rights Statement

In Copyright