2

Recently an AI poker program built by Facebook and Carnegie Mellon University had a profitable 12 day run against poker pros. The program was earning 10BB an hour at $50/100 against the likes of Jimmy Chou, Seth Davies, Michael Gagliano, Anthony Gregg, Dong Kim, Jason Les, Linus Loeliger, Daniel McAulay, Greg Merson, Nicholas Petrangelo, Sean Ruane, Trevor Savage, and Jacob Toole.

Artificial intelligence has been conquering the masters of games such as Go and Chess over the years, so is poker next?

| improve this question | |
  • 4
    I won't post an answer but I think, personally, no. I think because of the 'all-in' aspect it cannot be solved persay. Will bots become much better and be able to beat the game more and more? Yes, clearly given the above news. There certainly is a more optimal way to play. – Grinch91♦ Jul 12 '19 at 22:24
  • What's "all in" got to do with it? In fact, it's precisely because the game is finite (that is, there are a finite number of plays because you have a finite stake) that the game is most definitely solvable. Its still a bit out of reach for current computers, but not for long, which is why the current AI approach is more fruitful. But I suspect it will be solved before either Chess or Go is. – Lee Daniel Crocker Jul 15 '19 at 22:00
2

I saw this and thought it was pretty cool, but I do not think poker is "solved". This AI works by playing a large number of hands against players, mathematically analyzing the decisions it made in those hands, and applying those analytics to future decisions in future hands.

I personally do not think that this means that the AI has solved poker for a couple of reasons:

  1. This AI has only been able to master 6-max cash games against a small player pool. (Other AI's have been developed that can reliably beat top pros in heads-up play)

  2. It has achieved its level of play by learning, similar to how humans get better. This means that it will have a skill cap based on who it plays against because it will only be able to get good enough to beat them consistently. it will not get any better than that.

  3. If this AI plays against itself, I predict that it will reach a nash equilibrium fairly quickly because it will solely focus on playing perfectly optimally against itself, preventing the AI from being able to exploit itself in any way.

These are just my thoughts, and they probably have some kinks or exceptions involved. There is no doubt that this AI is very good at NLHE and it can most likely beat any player out there. I think that it has not yet solved the game though. In my opinion, the breadth of NLHE is much wider than chess or go because of all of the factors that must be taken into account when making a decision (of which there are very many). Things like exploitative play vs. GTO play, tournament strategies including ICM considerations, adjustments in larger games like 9-max games where players are constantly leaving and joining the table, and even information associated with live poker.

| improve this answer | |
  • 1
    Indeed, poker is not solved (with "solved" meaning the Nash equilibrium has been computed) except for a limited set of particular situations (mainly heads-up shortstack of push/fold simplifications). Needless to say, full-ring MTT play 200BB deep is miles away from being solved in the near future – David Jul 18 '19 at 22:33
  • By the way, what is so "cool" about ruining poker forever? – David Aug 20 '19 at 11:45
  • I think A.I. doing things like playing poker is cool. I dont think it will ruin poker forever. Who knows, it might be unsolvable. @David – Clarko Aug 21 '19 at 2:29
  • No. it's not unsolvable. There is a Nash equilibrium and it can be found with enough computer power. In a few years, playing for money online will no longer be an option, as everybody will be able to plug in his bot. I don't see anything cool about that – David Aug 21 '19 at 7:33
  • @David sorry you don't see it the way I do. I believe that it is relatively easy for poker sites to prevent bots from playing (if they try to), so I would not worry about online poker being ruined forever. – Clarko Aug 22 '19 at 2:56
0

I second Clarko's opinion. For no-limit holdem to be solved, you basically need a mathematical way or an algorithm that can be mathematically proven that you win or turn a profit all the time.

An AI being able to beat pros cannot be mathematically proven that it has the algorithm that guarantees it will always win or make money. It could be the best algorithm, but you will never know it is because it is trained to optimize some utility function.

I think there could be multiple version of texas holdem to be considered solved. It really first gets down to defining what is considered to be solved.

One way to define "solved" is that we come up with some algorithm that will guarantee you to turn a profit under certain environment.

Another way to define "solved" is that you come up with some algorithm that will guarantee you will have the most chip at the end of the game. My mathematical instinct tells me that this problem is going to be more difficult than the earlier one.

To conclude, we cannot considered AI beating human in poker as the problem being solved mathematically because you cannot mathematically prove what the AI is doing is indeed the correct algorithm.

| improve this answer | |
  • "Solved" is defined by computing the Nash equilibrium. When all the players play the NE, no player can benefit by playing something else. – Cohensius Jul 22 '19 at 13:04
  • I just read up on Nash equilibrium. I just had to ask this quesiton - why is it even interesting to study the nash equlibrium? Poker is zero sum game. Isn't it more interesting/useful to think of the game in terms of winning or being profitable? Why is important to study solving the nash equilibrium. Pardon me for my lack of knowledge in game theory. – Yao Hong Kok Jul 22 '19 at 20:48
  • since, if players do not play a NE, then some player have a beneficial deviation. NE is called equilibrium since once everybody play that strategy, there is a good chance they will continue to play that same strategy. – Cohensius Jul 23 '19 at 7:29
  • Nice! Thanks for explaining. – Yao Hong Kok Jul 23 '19 at 11:24
  • @YaoHongKok: Is it proven that a Nash equilibrium exists for poker, near which strategies can be transitively ranked? I would think that if a "strategy" was defined as producing a combination of actions and probabilities for any particular situation, someone who knew what strategy everyone else was using could formulate a strategy to beat them. – supercat Jul 31 '19 at 3:44
0

The researchers behind Pluribus were not even trying to solve 6max poker. Just prove that they can be less exploitable than some of the best players in the world. The did prove that.

Heads up no limit is not solved either, solving requiring as many decision points as the number of atoms in the universe.

Heads up limit is solved though.

Empirically though, what we know is that with reasonable computing power, doesn't take much to be less exploitable than humans, so we did get to a point where machines will beat humans in the long run forever now.

| improve this answer | |
  • They kind of "proved" that. They played under some conditions that clearly favour the bots. Also, I would like to see those machins play a deep-stack MTT against PROs, with a realistic time bank! – David Aug 19 '19 at 9:11
  • MTT this bot would lose now. It learned cash game with infinite bankroll. It has no notion of prize pools, ICM, etc. I suppose it could learn pretty easily though. – pierre derome Sep 2 '19 at 4:55
0

1- there is one or more Nash equilibriums to poker NLHE 6max and full ring. This is proven by Nash theorem and is explained here: https://www.cs.ubc.ca/~jiang/papers/NashReport.pdf

2- A Nash equilibrium is precisely a point where if both players know exactly the strategy of the other player, there is no way to exploit, ie deviate and benefit from it.

3- This has been found and solved for heads-up limit poker.

4- It has been proven to be unsolvable with computing power as we know it in our known universe for no limit due to the number of decision points. Same as Go which we can't solve.

5- Both Libratus and Cepheus have algorithms converging to Nash equilibrium for heads up nlhe. And have had trials with humans that they beat.

6- Pluribus has not been proven to converge to Nash equilibrium, it does reduce exploitability with each "learning cycle" though. And did reach algos where it statistically beats real top pros.

7- Pluribus does not attempt to reduce variance and as such assumes infinite bankroll. IE in real life it would go bankrupt pretty often before winning big money. In the highly publicised match again,st pros, it did lose 70K$ actually.

| improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.