Noam Brown

I think No Limit Texas Hold'em, the version that we were playing has 10 to the 161 different decision points, which is more than the number of atoms in the universe squared.

That's heads up.

Yeah.

I mean, it depends on the number of chips that you have, the stacks and everything, but the version that we were playing was 10 to the 161.

Oh, no, no, no.

I'm saying we played the full game.

You can bet whatever amount you want.

The bot maybe was constrained in what it considered for bet sizes, but the person on the other side could bet whatever they wanted.

And so the way neural nets help out here is, you know, you don't have to run into the same exact situation because that's never going to happen again.

The odds of you running into the same exact situation are pretty slim.

But if you run into a similar situation, then you can generalize from other states that you've been in that kind of look like that one.

And you can say like, well, these other situations, I had high regret for this action.

And so maybe I should play that action here as well.

That is a controversial question.

I'm sure David Silver is going to get really angry at me.

I'm going to say poker, actually, and I think for a couple reasons.

So first of all, you have the imperfect information aspect.

And so we can go into that.

But once you introduce imperfect information, things get much more complicated.

Yeah, so Texas Hold'em, you get two cards face down that only you see.