Noam Brown

It wasn't until much later that I actually worked on poker AIs.

Yeah, checkers are completely solved.

Optimal strategy.

It's impossible to beat the AI.

You could solve chess.

You could solve poker.

So this gets into the concept of a Nash equilibrium.

Okay.

So...

In any finite two-player zero-sum game, there is an optimal strategy that if you play it, you are guaranteed to not lose an expectation no matter what your opponent does.

And this is kind of a radical concept to a lot of people, but it's true in chess, it's true in poker, it's true in any finite two-player zero-sum game.

And to give some intuition for this, you can think of rock, paper, scissors.

In rock, paper, scissors, if you randomly choose between throwing rock, paper, and scissors with equal probability, then no matter what your opponent does, you are not going to lose an expectation.

You're not going to lose an expectation in the long run.

Now, the same is true for poker.

There exists some strategy, some really complicated strategy that if you play that, you are guaranteed to not lose money in the long run.

And I should say, this is for two-player poker.

Six-player poker is a different story.

Poker is a very high variance game.

So you're going to have hands where you win.