I would like to invite you to attend and consider submitting papers for the AAAI-17 Workshop on Computer Poker and Imperfect Information Games. As you probably know, it is the main forum where people interested in computational poker regularly meet in person and discuss their research. The deadline for paper submissions is November 4 and more details about the event can be found on the workshop web page: https://sites.google.com/a/ualberta.ca/cpw2017/. Thank you for considering your participation.
The Annual Computer Poker Competition will be held again in 2017, during the month of January. Martin Schmid will be the incoming chair of the competition for this year and Kevin Waugh will be returning as the outgoing chair. This time, only the heads-up (two player) no-limit Texas Hold'em competition will be held.
The plan is to use Amazon EC2 instances again this year, with a final submission deadline of Friday January 13, 2017. Note that these machines are quite a bit less powerful than many desktop machines, so if computing resources are a significant issue for you, please check that this is adequate. We have increase the maximum submission size to 250 GB this year. The remaining technical specifications remain the same as last year. See http://aws.amazon.com/ec2/instance-types/ for details on Amazon instance types. It is possible to get access to a smaller testing instance through Amazon for free by creating an EC2 account, and all competitors will get access to a full sized competition machine for final testing at least one week prior to the final submission deadline.
Unfortunately, the results announced at AAAI 2016 workshop were erroneous. In particular, the additional matches that were run to separate the top four agents, seeds 100 and higher, were biased as all these matches used the same sequence of cards. We gratefully thank Vahe Hagopian who brought this to our attention.
This introduced bias invalidates the previously posted results for the Bankroll Instant Runoff competition, where in a sense it resulted in an effective sample size of two between the top agents.
To correct this error, additional matches between the top four, and subsequently the top two agents, were run. The log files, crosstable and ordering have been corrected on the results page; an errata has been added; and measures to prevent this particular error from occurring again have been implemented.
The Bankroll Instant Runoff winners are: