Symposium logo


The 2012 Computer Poker Symposium at AAAI is designed to be a forum where researchers studying Computer Poker and other games of imperfect information can share current research and gather ideas about how to improve the state of the art and advance AI research in these areas.

In recent years, poker has emerged as an important, visible challenge problem for the field of AI. Just as the development of world-class chess-playing programs was considered an important milestone in the development of intelligent computing, poker is increasingly being seen in the same way. Several important features differentiate poker from other games: the presence of imperfect information (due to hidden cards), stochastic events, and the desire to maximize utility instead of simply winning. Hence, traditional AI game-playing techniques do not apply and novel methods are required.

Topics of interest include anything related to the computer version of poker or other games of imperfect information. This includes descriptions of novel competitors or components of competitors from recent or future AAAI Annual Computer Poker Competitions, as well as research on any topics related to games of imperfect information.


The Computer Poker Symposium will consist of a series of oral presentations, followed by a poster session and discussion. The results of the 2012 AAAI Annual Computer Poker Competition will also be announced during the Symposium.
Here is a preliminary schedule for the symposium [pdf]


The Computer Poker Symposium is scheduled from 1:00 - 5:00pm on Monday, July 23, 2012 in Conference B/C on the Mezzanine Level of the Sheraton Centre Toronto Hotel.


Slumbot: An Implementation of Counterfactual Regret Minimization on Commodity Hardware [pdf]
Eric Jackson

Counterfactual Regret Minimization and Domination in Extensive-Form Games [pdf]
Richard Gibson

Tartanian5: A Heads-Up No-Limit Texas Hold'em Poker-Playing Program [pdf]
Sam Ganzfried, Tuomas Sandholm

Safe Learning in Zero-sum Games [pdf]
Kevin Waugh, Michael Bowling

Sartre3P: A Case-Based Multiplayer Poker Agent [pdf]
Jonathan Rubin, Ian Watson

Combining Various Strategies in a Poker-Playing Multi-agent System [pdf]
Bojan Butolen, Milan Zorman

Calculating the Exploitability of Heads-Up Limit Agents [pdf]
Michael Johanson


Applying Reinforcement Learning to Poker [pdf]
Neill Sweeney, David Sinclair

Active Sensing for Opponent Modeling in Poker [pdf]
Adam Eck, Leen-Kiat Soh

Computer Poker Research at LIACC [pdf]
Luis Filipe Teofilo, Luis Paulo Reis, Henrique Lopes Cardoso, Dinis Felix, Rui Seca, Joao Ferreria, Pedro Mendes, Nuno Cruz, Vitor Pereira, Nuno Passos

The Spewy Louie Poker Bot [pdf]
Jon Parker, Chris Wacek


If you have any questions or comments, please contact us at