I'm one of the authors of the bot, AMA
What sort of defense applications could this sort of technology be used for? The last line of the Facebook blog post sparked curiosity.
No limit: AI poker bot is first to beat professionals at multiplayer game
111–120 of 407 posts
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#112Earlier quoted context omitted.
Have you thought about open sourcing the non-AI pieces? It would be great for other researchers so they wouldn’t have to build the poker pieces from scratch
There is some open-source code in this area, and hopefully there will be more going forward. Here's one example: https://github.com/EricSteinberger/Deep-CFR
a. Is CFR applicable in single player hidden-information games? (e.g. state is initially hidden, gradually revealed to the agent, but there is not adversary)
b. How much more efficient is the improved search algorithm? the $150 number sounds like a couple of order of magnitudes..
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#113I'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…
I think it took the community a while to come up with the right algorithms. So much of early AI research was focused on beating humans at chess and later Go. But those techniques don't directly carry over to an imperfect-information game like poker. The challenge of hidden information was kind of neglected by the AI community. This line of research really has its origins in the game theory community actually (which is why the notation is completely different from reinforcement learning).
Fortunately, these techniques now work really really well for poker. It's now quite inexpensive to make a superhuman poker bot.
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#114I'm one of the authors of the bot, AMA
When will you test it with 10 total players in a game?
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#115So, is this the end of online poker? Will it just become increasingly sophisticated bots playing each other online?
I'm really confused about why stock for the company that makes PokerStars hasn't moved at all today: https://www.google.com/search?tbm=fin&q=TSE:+TSGI#scso=_wqsn... The fact that there's a published recipe for a superhuman bot that can be trained for $150 and run on any desktop computer sounds like an existential threat to their business. The main mitigating factor I can think of is that you'd need to also adversaria…
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 as the "dumb money" slowly dries up.
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#116Hi Noam: I'm intrigued that you trained/tested the bot against strategies that were skewed to raise a lot, fold a lot and check a lot, as well as something resembling GTO. Were there any kinds of table situations where the bot had a harder time making money? Or where the AI crushed it?
I'm thinking in particular of unbalanced tables with an ever-changing mixture of TAG and LAG play. I've changed my mind three times about whether that's humans' best refuge -- or a situation that's a bot's dream.
You've done the work. Insights welcome.
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#117I'm one of the authors of the bot, AMA
Who were the pros? Are they credible endbosses? Seth Davies works at RIO which deserves respect but I've never heard of the others except Chris Ferguson who I doubt is a very good player by todays standards (or human being, for that matter), but I've never heard of the others when I do know the likes of LLinusLove (iirc, the king of 6max), Polk and Phil Ganford. Is 10,000 hands really considered a good enough sample?…
LLinusLove was one of the players. Chris Ferguson was in one of the 5 AI's + 1 Human experiment but not the 5 Humans + 1 AI experiment.
We used AIVAT to reduce variance, which reduces the number of samples we need by roughly a factor of 10: https://poker.cs.ualberta.ca/publications/aaai18-burch-aivat...
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#118Was this cash or tourney format? How many blinds deep was the bot and the rest of the players at the start?
From the sample hands, it looks as if it's a cash game with stacks equal to 200BB. Plenty of room to play real poker.
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#119isnt it just possible that the bot got lucky. It plays good. Maybe really good but does it play as good as a pro??? Would it win 9 wp bracelets. Would It make it to day 3 of the world series of poker.
Chris Moneymaker got some damn good hands. Its part of the game. Its why this feat is unremarkable and why poker is a crap game for AI. The outcomes are very loose, especially when the reason these guys are pros is partially because of their ability to read.
You are taking away a tool that made their proker players great and then expect them to be a metric to test the AI. A better test would be to have pro players play a set of 1, 2, 4, 7 basic rule bots and the AI does the same. Then you compare differences in play. With enough data points you can compare situations that are similar but the AI did better or worse. This is a fair comparison of skill.
Also if there are professional players at a multiplayer game the AI is getting help from other players. Just like Civ V I get help from the AI attacking itself. Im sure this AI got help from the players attacking eachother (especially if they were doing so and making the pot bigger for the AI to grab up, think of a player reraising another player after the bot does a check all in).
Re: No limit: AI poker bot is first to beat professionals at multiplayer game
#120I'm one of the authors of the bot, AMA
When will you test it with 10 total players in a game?
The number of players is kind of arbitrary given the techniques we're using. We chose 6 because that's the most popular/common format for poker. I don't think there's any scientific value in also doing 10.