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

No limit: AI poker bot is first to beat professionals at multiplayer game

nature.com

Post reply on HN
Print view View original

221–230 of 407 posts

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#221

Post by YeGoblynQueenne »

pesenti wrote: post #2

Blog post: https://ai.facebook.com/blog/pluribus-first-ai-to-beat-pros-... Science article: https://science.sciencemag.org/content/early/2019/07/10/scie...

>> Pluribus is also unusual because it costs far less to train and run than other recent AI systems for benchmark games. Some experts in the field have worried that future AI research will be dominated by large teams with access to millions of dollars in computing resources. We believe Pluribus is powerful evidence that novel approaches that require only modest resources can drive cutting-edge AI research.

That's the best part in all of this. I'm not convinced by the claim the authors repeatedly make, that this technique will translate well to real-world problems. But I'm hoping that there is going to be more of this kind of result, singalling a shift away from Big Data and huge compute and towards well-designed and efficient algorithms.

In fact, I kind of expect it. The harder it gets to do the kind of machine learning that only large groups like DeepMind and OpenAI can do, the more smaller teams will push the other way and find ways to keep making progress cheaply and efficiently.

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#222

Post by patrickfreed »

splonk wrote: post #161
MFLoon wrote: post #50

Earlier quoted context omitted.

When human players donk bet it's almost always a weak player employing an extremely exploitable strategy, whereas pros almost never do it because the metagame has evolved around the presumption that nobody ever donk bets. I'd love to see what the bot's balanced GTO donking strategy looks like.

It's basically been true along every step of the the poker bot evolution (HU limit, HU NL, and 6-max NL) that the bots donk a lot more than the humans. 10 years ago you could find pros arguing that donking in any situation is always wrong. That's been shifting for years, but still not to the level that the bots do it. My personal belief is that the "no-donk" strategy is an adaptation by fallible human minds to reduce…

Your personal belief is likely correct. Balancing a donking range is incredibly difficult for humans and doing so perfectly likely yields only a very small EV bonus over just always checking. For humans it makes a whole lot of sense to reduce the branching in a case like that whereas for computers it doesn't really matter.

Another good example is varying continuation betting sizes. A true GTO strategy would mix in a number of different sizings (and I'm sure the bots adapted to do this), but you only sacrifice a very tiny amount of EV by basically betting the same size every time. Doing the latter limits humans risk for making errors which is far more valuable than squeezing out .05bb/100 more by varying the sizes.

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#223

Post by slashcom »

grandtour001 wrote: post #207

Were the games played with real money? Nobody is going to take fake money games seriously.

From the paper:

"$50,000 was divided among the human participants based on their performance to incentivize them to play their best. Each player was guaranteed a minimum of $0.40 per hand for participating, but this could increase to as much as $1.60 per hand based on performance."

So the humans weren't betting their own money, but they still made more money if they won.

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#225

Post by dbancajas »

csa wrote: post #143
friendlybus wrote: post #109

Earlier quoted context omitted.

Post blizerian's time in poker, the human players in online games use statistics to make insane bets on odds. They play many many games at once and just look for the opening and make the insane bets when the openings come up. They've done the math that it's worth it to do those kinds of bets.

I did this with great success. For reference, I once folded top boat to quads (he showed) to a river all in raise in PLO to a dude who had a 100% win showdown when raise river stat over several thousand hands. Other stats confirmed he was a nit, so it was an easy fold. Iirc, this was PLO 200 or PLO 400 — I never saw anyone that nitty at the PLO 1000 or PLO 2000 tables. FWIW, I did a lot more than “look for an opening…

do you still play online? I used to railbird FT back then, watching patrick antonius/sahamies/durr/jungleman etc. exciting times. How many hours did you put in for you to be good?

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#226

Post by chongli »

oppiz wrote: post #193
oppiz wrote: post #191

Earlier quoted context omitted.

It's my understanding the big sites have some pretty sophisticated bot detection systems, so in theory a bot that would be successful at beating online poker couldn't be a huge winner, it'd presumably raise too many red flags. However, if it were a near break-even player, with dozens, if not hundreds, of instances running at any given time, it's going to slowly grind out a substantial figure. You'd also have to take…

I guess the real threat isn't a "bot" but something in the way of a program that interprets the data on the screen real-time and whose output instructs the player of the "optimal" play, given the circumstances. How the hell would you deter that as a site operator?

No, I think your earlier example of a swarm of just-above-break-even bots would be much more difficult to combat. Even if they can be detected, the anti-detection countermeasures can evolve, turning it into an arms race. Anything you can model in your bot detection algorithm, the bot-maker can model too.

Reaction times ought to be one of the easiest things to fake. All it would take is a bunch of monitoring of large numbers of games to create a nice model of real player reaction times, which in all likelihood are normally distributed anyway.

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#227

Post by dbancajas »

friendlybus wrote: post #109
ehsankia wrote: post #86

Earlier quoted context omitted.

This is something I've always wondered, how come bots haven't taken over online poker considering how much money there is to be made, and all you need is to be slightly better than average right? Is high level poker really that hard to achieve?

Post blizerian's time in poker, the human players in online games use statistics to make insane bets on odds. They play many many games at once and just look for the opening and make the insane bets when the openings come up. They've done the math that it's worth it to do those kinds of bets.

what is post bilzerian time mean? I heard bilzerian's game was not gooda and rumor has it his using poker as a front of how he earned money??

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#228

Post by dbancajas »

bcassedy wrote: post #152
asdfman123 wrote: post #115

Earlier quoted context omitted.

You know, now that we're talking about it I'm wondering if someone hasn't already come up with a better bot and has just been silently using it to win money online. I'm sure the sites have been crawling with bots as long as they've been around, some better than others. As long as it doesn't drive away too many customers I doubt the sites care. They still take a rake on bot games. However better AI could change that a…

Dumb money has been drying up for years. There have been bots taking millions of dollars out of games for more than a decade. Even bots from 10 years ago were sophisticated enough to win money at mid-stakes poker (up to $2000 buy in 6max no limit games)

proof? I dont' believe this. 2K buy-in has a lot of regs that are pretty good overall in cash games. Plus Pokerstars/FT has a pretty good anti-bot policy. if you get caught bye bye to the $.

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#229

Post by icelancer »

n3k5 wrote: post #104
noambrown wrote: post #6

I'm one of the authors of the bot, AMA

What took you so long? I mean not the Pluribus team specifically, but Poker AI researchers in general. The desire to master this sort of game has inspired the development of entire branches of mathematics. Computers are better at maths than humans. They're less prone to hazardous cognitive biases (gambler's fallacy etc.) and can put on an excellent poker face. As a layperson who's rather ignorant about both no-limit…

>> Computers are better at maths than humans.

OP discussed it but while this is true, it is not necessarily true or straightforward when it comes to games with hidden information like poker. This is more of a game theoretical problem (Economics) than it is a purely mathematical one, which had less support in the AI/ML community, hence the delay.

The lower CPU/GPU/resource use supports that fact as does your intuition. Breaking poker required a lot of manual work and model design over brute force algorithms and reinforcement learning.

Re: No limit: AI poker bot is first to beat professionals at multiplayer game

#230

Post by icelancer »

joaomacp wrote: post #133
amelius wrote: post #130

Earlier quoted context omitted.

So will this be the end of online poker?

It must be. It is way too hard to prevent humans from using an AI. Some chess services try to check if you're playing "too perfect", but in poker that's harder to do, and there's way more money on the line.

>> Some chess services try to check if you're playing "too perfect", but in poker that's harder to do, and there's way more money on the line.

Not really. With perfect information you know the correct strict equity plays assuming normal opponents. This doesn't give you the ultimate answer, because a player's reads and inference about another player is definitely an input - especially at the highest level - but it is more than enough to give you a winning/losing player at the small/midstakes.

source: worked for an online poker company that had these tools... and far more available to us

Post reply on HN