Artificial Intelligence in Poker

OData support
Rajacsics Tamás
Department of Automation and Applied Informatics

In the field of artificial intelligence research a common method to test new theories and algorithms is to try them in different games with different rules. After the success in chess and other games with perfect information the attention started to shift to games like poker where the already known methods weren’t efficient enough.

The capability of poker bots progressed tremendously in the last decades with new algorithms discovered. With game theory and opponent modelling methods, such bots were created that could even compete with a professional player too.

The purpose of this thesis is to show the different kinds of poker intelligences and the algorithms behind them which was used to create the most successful poker agents. The creation of these bots can be tied to the Canadian University of Alberta Computer Poker Research Group [1] who created the strongest poker agents in the world and made their results available. This thesis shows the achievements of poker artificial intellgience through their work.

The second part of the thesis is about showing a poker game program created by myself. With the creation of the game I had the opportunity to make some simpler poker agents and analyze them.


Please sign in to download the files of this thesis.