Sign In

Communications of the ACM

ACM TechNews

Carnegie Mellon's Pokerbot Models Asymmetric Data

A fictional poker-playing robot.

The Baby Tartanian 8 pokerbot created by a team from Carnegie Mellon University won first place in the total bankroll category of the Annual Computer Poker Competition.

Credit: 20th Century Fox Television

Carnegie Mellon University's (CMU) Pokerbot, called Baby Tartanian 8, won first place at the Annual Computer Poker Competition in the total bankroll category and third place in the bankroll instant run-off category, out of 11 participating teams.

The Baby Tartanian 8 project is representative of an incomplete information problem, and aims to be able to find and play the strategy with the best results, based on limited information. The algorithm is not specific to poker, and "should be generally applicable to any strategic interaction where you have multiple agents and asymmetric information," says CMU researcher Noam Brown.

Asymmetric information is a situation in which one person has information that the other person does not. "In a game like poker, where you have a lot of actions available to you, pruning helps cut down to actions that are worth investigating according to a given situation, instead of considering all the actions available to you," Brown notes.

The researchers used the pruning technique to minimize the options that would be investigated by the system, while ensuring the algorithm still arrives at an optimal strategy.

Future plans for the Tartanian model involve upgrading the algorithm and equipping it with better hardware more suited to perform higher computation levels.

From Tartan Online (Carnegie Mellon University)
View Full Article


Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account