Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

How A.I. Conquered Poker

nytimes.com

Post reply on HN
Print view View original

81–90 of 188 posts

Re: How A.I. Conquered Poker

#81

Post by perfect_wave »

isaacg wrote: post #20
marcodiego wrote: post #6

Is there any remaining logic game which AI hasn't become superhuman? IIRC Monte Carlo tree search has done wonders in this area.

As far as I know, in Magic: the Gathering, the best bots are far worse than most players. Part of the difficulty is that the rules are so complicated that there are only a couple of complete rules implementations. Beyond that, it's an imperfect information game with far more actions per game than poker, so optimal-solver techniques haven't seen success.

An MTG limited player named Ryan Saxe created an AI that drafts and builds deck to a highly successfully degree: https://github.com/RyanSaxe/mtg

He was able to reach Mythic, the highest ranking tier on Magic Arena. Of course this is a different problem to actually playing the game (and probably significantly easier). That being said, this is one guy doing it as a side project with restricted resources.

I imagine that MTG could played quite successfully by an AI if someone where to dedicate the resources. Imo much of the difficulty is in laying the groundwork. Large amounts of data don't exist publicly and laying the framework for a bot to play itself would be quite difficult (and then the computation costs would be extremely expensive).

Re: How A.I. Conquered Poker

#82

Post by GoatOfAplomb »

DennisP wrote: post #79
splonk wrote: post #52

(Former pro and high stakes player, occasional solver developer) This is actually one of the best poker articles I've ever seen in generalist media. Not too clickbaity, reasonable high level overview of game theory, a (very accurate IMO) quote from old pro Erik Seidel about the state of the game just 15 years ago, a discussion on variance vs. EV and results, and most importantly, an emphasis on math, randomization te…

Interesting, I read some Sklansky books about 15 years ago and he talked about semibluffs, where you're partly bluffing but you've also got some chance to win. Sounds like strategy has evolved into doing the exact opposite.

The distinction is that semi-bluffs are for when there are still cards to be dealt.

Re: How A.I. Conquered Poker

#83

Post by sillysaurusx »

splonk wrote: post #52

(Former pro and high stakes player, occasional solver developer) This is actually one of the best poker articles I've ever seen in generalist media. Not too clickbaity, reasonable high level overview of game theory, a (very accurate IMO) quote from old pro Erik Seidel about the state of the game just 15 years ago, a discussion on variance vs. EV and results, and most importantly, an emphasis on math, randomization te…

So how much have you won and lost in total? I don’t have any knowledge of poker, so I don’t know how to ballpark this. And the impersonal questions are boring after seven lifetimes, so I thought I’d ask.

It would be interesting to see a GitHub style graph of poker activity, with won and lost corresponding to added lines and removed lines.

Re: How A.I. Conquered Poker

#84

Post by sillysaurusx »

bluecalm wrote: post #9

I am the solver programmer mentioned in the article. I think it came out pretty decently. Maybe not all the details are right (I was late answering fact checking email) but I think it's a decent read and the author has done a good job!

How did you end up working on this?

It’s an interesting history.

Re: How A.I. Conquered Poker

#85

Post by DennisP »

GoatOfAplomb wrote: post #82
DennisP wrote: post #79

Earlier quoted context omitted.

Interesting, I read some Sklansky books about 15 years ago and he talked about semibluffs, where you're partly bluffing but you've also got some chance to win. Sounds like strategy has evolved into doing the exact opposite.

The distinction is that semi-bluffs are for when there are still cards to be dealt.

Ahh, ok thanks.

Re: How A.I. Conquered Poker

#86

Post by karpierz »

jdmoreira wrote: post #55
dwohnitmok wrote: post #51

Earlier quoted context omitted.

I think this is purely a resource issue, e.g. if Google Brain decided to make an MtG bot I would be fairly confident it would be superhuman. Even real time strategy games like Starcraft are looking like they're on the cusp of superhuman bots (Alphastar was competitive as Protoss against elite players, but did not consistently beat them).

The search tree is huge in mtg. It has to be the largest of any game. You can take actions all the time. There are triggers all the time, you can stack your actions on top of your opponent actions. Huge space really. And then of course it's also imperfect information both in the sense of your opponent hand but also his deck. The cardpool is also very large for some formats. I actually don't think it's solvable just b…

The search tree size isn't an insurmountable issue. For exple OpenAI 5 managed to play DotA (though admittedly relied heavily on perfect timing and the ability to look at every enemy on the minimap at the same time, and lost a lot when people learned to play around the only strategy it knew).I think it'd be feasible to get an AI to play a modern deck.

I think it'd be much harder for the AI to do deck building in a vacuum. You could model it as every game starting with you building your deck, but I can't see that converging stably.

Re: How A.I. Conquered Poker

#87

Post by HWR_14 »

ska wrote: post #16
HWR_14 wrote: post #15

Earlier quoted context omitted.

I'm surprised that Hanabi is such a huge research area. Compared to bridge or poker, it seems like a far more simple game.

> I'm surprised ... it seems like a far more simple game. This probably shouldn't surprise you. If you are researching how to attack a new/difficult class of problems, typically you look for the simplest versions of that class first.

I would agree with that. I just tended to assume that Hanabi would be a solved problem by now.

Re: How A.I. Conquered Poker

#88

Post by bloodyplonker22 »

smallerfish wrote: post #57
bloodyplonker22 wrote: post #30

Earlier quoted context omitted.

Online poker has already been evolving in this direction. Any serious player who plays online will use player assistance tools (such as PIOsolver). Top level poker AI such as Pluribus has already proven that it can hold its own and beat the best online players such as linuslove. It is well known that online poker sites are full of poker bots now. There are programs to help users try to tell if they are playing agains…

Yeah, that was the evolution of my thought process. Online poker is already full of bots, which will get more and more sophisticated over time and defeat bot detection hurdles -- so why not embrace it and have bot-only zones? You could have entire tournaments play out in less than a minute if all participants were software.

because humans are the worst players in most cases now. Especially at the lower limit tables. Obviously, you want to play the worst players to make the most money.

Re: How A.I. Conquered Poker

#89

Post by noambrown »

HWR_14 wrote: post #87
ska wrote: post #16

Earlier quoted context omitted.

> I'm surprised ... it seems like a far more simple game. This probably shouldn't surprise you. If you are researching how to attack a new/difficult class of problems, typically you look for the simplest versions of that class first.

I would agree with that. I just tended to assume that Hanabi would be a solved problem by now.

Bots are superhuman in self-play Hanabi: https://ai.facebook.com/blog/building-ai-that-can-master-com...

The remaining challenge is getting it to play well with human partners. Doing that requires modeling human conventions rather than learning weird bot conventions. That's hard because while you can collect essentially unlimited data through self play, it's hard to collect a lot of data playing with humans using reinforcement learning. AI algorithms are really bad at sample efficiency.

Re: How A.I. Conquered Poker

#90

Post by bloodyplonker22 »

cortesoft wrote: post #65
bloodyplonker22 wrote: post #30

Earlier quoted context omitted.

Online poker has already been evolving in this direction. Any serious player who plays online will use player assistance tools (such as PIOsolver). Top level poker AI such as Pluribus has already proven that it can hold its own and beat the best online players such as linuslove. It is well known that online poker sites are full of poker bots now. There are programs to help users try to tell if they are playing agains…

I would expect bots to add random delays? They could even determine real player delay distributions and emulate that.

yes, that is the obvious step that bot makers have taken. When bots were barely at the online poker scene, nobody cared to even check. Of course, there are still other ways to check for bots such as a user playing for an unreasonable amount of time or an extraordinary amount of tables, or simply not answering to chat.
Post reply on HN