the incomprehensible challenge of poker

When reading in Nature about two deep learning algorithms winning at a version of poker within a few weeks of difference, I came back to my “usual” wonder about poker, as I cannot understand it as a game. (Although I can see the point, albeit dubious, in playing to win money.) And [definitely] correlatively do not understand the difficulty in building an AI that plays the game. [I know, I know nothing!]

2 Responses to “the incomprehensible challenge of poker”

  1. Dear Xian,

    This cool blog post helped me understand some of it: http://www.sirlin.net/articles/solvability
    In a nutshell, part of the draw and complexity of poker is that playing the Nash-equilibrium solution is not actually what you want to do, because your opponent is not perfect. You want to detect how your opponent strays from optimality and punish his deviations.*
    Furthermore, since your opponent is also trying to do that, you also want to appear to have deviations from optimality so that you can punish his reactions.

    Guillaume

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s