Introduction to Poker AI: The science of getting paid for information

Venue Capacity: 60 people The capacity of the venue is about 60 people but because of no-shows, we have a policy of first-come, first-served on the night in the event of the room filling up. Managing no-shows is a problem all Meetups have to deal with and this is the fairest method we can think of. While we have never been in a position to turn anyone away for capacity reasons, it is always a possibility, so please arrive early to avoid disappointment on the night. Games are a popular test-bed for AI. They provide concrete examples which are usually both reasonably simple to describe and yet are not trivial to solve. Poker is a set of games which centre on balancing using and hiding private information, as well as discerning hidden information held by the the other players. This talk will giver an overview of Poker AI Research. It will include sections on Game Theory; Poker Rules; Basic Poker Strategy; Overview of Top-Level Poker AIs; Overview my own efforts; Recent Matches between AIs and top-level humans. Hopefully, at the end of this talk, you will learnt a new way of thinking about situations that may involve deception, some new vocabulary (I'll explain what a “Crying Call” and a “Float” is), something about how AI can cope in those situations and about the importance of basic statistical theory, even in high-end research. ** About me ** Career summary: Applied Maths Degree, Maths-Physics M.Sc., Maths Lecturer/Tutor, Poker AI Ph.D., Milk Meter Calibration, Car Rental Recommender. Applied Maths nerd by inclination: I like well-framed theories that result in working prototypes (I still think of it as Applied Maths even if the cool kids are calling it AI.) Particularly interested in Decision Theory and related subjects; information is only valuable when it generates better decisions. I won't mention reinforcement learning much this time but my previous Meetup talk for Dublin R is here: https://files.meetup.com/2755912/RL meetup.zip I'll put the slides for this talk up somewhere (probably on ResearchGate) when I have them finalised. Okay, as promised https://www.researchgate.net/publication/329590489_Poker_AI_overview_for_Dublin_Data_Science_Meetup