University Thesis- Poker A.I.

[Flint{$N}]

Hey all,

Haven't made too many posts, but heres another.

I'm looking into creating Artificial Intellegance for limit hold em. I have just started to think about it as a thesis topic for school recently. I'm actually meeting with a professor this week to disscuss.

I'm pretty sure A.I. has been attempted before. If so, do you know who created it and if it was successful? I'm going to read up on the wilson software and see what sort of things they have done.

So a thesis on strucutred hold em AI, what do you think?

Flint

[Schizo]

You do realize that a lot of people that post in this forum make a living via online poker don't you? What kind of responses are you expecting to get?

[Flint{$N}]

I pay my rent and tuition through multi table grinding.

In my mind, playing against an A.I. would be the same, or even easier than playing true players.

The feedback that I'm looking for is purely opinionative. I'm just curious as to what people think or if I should even bother becuase theres something already out there.

[Schizo]

[ QUOTE ]
I'm just curious as to what people think or if I should even bother becuase theres something already out there.

[/ QUOTE ]

Yes, there is something out there. And I doubt very many people are going to be very happy.

[Rocco]

Interesting post... If I'd be able to do my thesis over again, I would definitely try something in line with a neural network learning to play Fixed Limit Texas Hold'em. Though, as I remember it, my lecturer on Artificial Neural Network made it clear that attempts to create a neural network that plays good in a game where you don't have full-state information, often fail. Learning through temporal differencing have been successfully applied to chess and backgammon for example, but never really learned to play bridge.

Moreover, if you (a good player) know you're up against some kind of a bot, you have enough tools in your bag of tricks to outplay it, I believe. You are probably able to construct a neural network that will play like an average player. Though, I wouldn't trust my "bot" with my bankroll, leave it on while going to work and come back home only to find out it has lost you $3000.

Now, I googled for "neural network" + "hold'em" and found a few interesting thesis on the subject. All of them confirmed my suspicions... But still, go ahead and do the thesis. Even if your bot fails to play good, you will still graduate having spent your last term playing and thinking poker [img]/images/graemlins/smile.gif[/img]

Good luck!

[theRealMacoy]

by now i am sure you are aware of the university of Alberta AI research with regard to poker. they have been underway for at least the last 10 years and developed Poker Academy Pro (formerly Poki) and other programs.

cheers,
the Real Macoy

[sfer]

Your inability to do a routine literature search on your subject should concern you a lot if you're planning on undertaking a big research project.