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

231–240 of 407 posts

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

#231

Post by icelancer »

b_tterc_p wrote: post #162
noambrown wrote: post #6

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

The bot does not seem to consider previous hands in its decisions. That is to say, it does not consider who it is playing against. Should this affect how we perceive the bot as “strategic” or not? Bots that play purely mathematically optimally on expected value aren’t effective or interesting. But it feels like this is playing on just a much higher order expected value. It feels like a more down to earth version of t…

>> Bots that play purely mathematically optimally on expected value aren’t effective or interesting.

Interesting is up to you, but effective is definitely wrong.

ICM-perfect bots crush small tournaments, which do not take into account opponent behavior - merely modeling the gamestate. The faster the blinds and the smaller the stacks, the better, but even normal structures get killed by these so-called "expected value" only bots.

Game Theory Optimal (GTO) attacks are incredibly effective at all levels of the game. The AI need not incorporate opponent feedback to be a winner. It can make it better, but it is not at all required.

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

#232

Post by icelancer »

bluetwo wrote: post #202
wallawe wrote: post #102

Earlier quoted context omitted.

> In Tourney play, the top 2 or 3 players get paid out Or top 2 or 3 thousand... depends on the tournament but it's usually the top 15% ish.

True, I am thinking "sit and go" tournament where you would have 6 players like in this research.

Is there much to do here? ICM bots have this space covered pretty effectively.

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

#233

Post by noambrown »

solidasparagus wrote: post #213

So Dota 2 doesn't count as a multiplayer game? OpenAI Five beat the world champions in back-to-back games...

From an AI and game theory standpoint, there isn't much difference between two-team zero-sum and two-player zero-sum if the teammates are trained together. That said, the Dota 2 work is extremely impressive for a variety of other reasons.

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

#234

Post by icelancer »

throwamay1241 wrote: post #84
noambrown wrote: post #6

I'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?…

What? The pros chosen were definitely highly skilled players. They're fairly well known in the online poker community.

Furthermore, Chris Ferguson, scumbag aside, is absolutely still a very good player by today's standards, and one way higher than the mean participant in a research experiment.

10,000 hands is an effective enough sample at a certain win rate and analysis of variance of play; the n-value alone is not enough to tell you if it was enough hands.

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

#235

Post by icelancer »

nradov wrote: post #151
anbop wrote: post #100

Earlier quoted context omitted.

Well if they upset the poker world do you think they would have top pros willing to go on record endorsing them?

Top pros will endorse whatever they're paid to endorse.

This is falsifiable by any number of cases, but Isaac Haxton spurning PokerStars is probably one of the best examples so others see your comment is not universally applicable.

https://upswingpoker.com/isaac-haxton-pokerstars-partypoker/

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

#236

Post by noambrown »

w_s_l wrote: post #153
noambrown wrote: post #6

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

will you release the source code?

Our goal is to make the research as accessible as possible to the AI community, so we include descriptions of the algorithms and pseudocode in the supplementary material. However, in part due to the potential negative impact this code could have on online poker, we're not releasing the code itself.

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

#237

Post by solidasparagus »

taejavu wrote: post #220
solidasparagus wrote: post #213

So Dota 2 doesn't count as a multiplayer game? OpenAI Five beat the world champions in back-to-back games...

Yes, Dota 2 is not a multiplayer poker game. I agree that the title is ambiguous, but it's not a stretch to imagine that "poker" is implied here.

I don't think it's implied considering the articles compares the poker bot to go and chess bots (which are the non-multiplayer games the title is referring to).

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

#238

Post by icelancer »

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…

If true in cash games, it is funny since it is a not uncommon strategy in high-level tournament play to control pot size.

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

#239

Post by barry-cotter »

b_tterc_p wrote: post #189
noambrown wrote: post #178

Earlier quoted context omitted.

The bot bluffs, and understands that when its opponent bets it might be a bluff. I would consider that to be strategic behavior. The fact that its strategy is determined by a mathematical process doesn't change that in my opinion.

It does bluff, but that’s not my point. My issue is that it bluffs without consideration of its opponent. High level strategic play of most games is about adapting to your opponents play. This bot does not do that. It is secretly a giant lookup table of game state to response. In the case of poker, it appears that adaptability is not as good as pure mathematical optimization. Humans can adapt their strategy, but it’s…

> In the case of poker, it appears that adaptability is not as good as pure mathematical optimization. Humans can adapt their strategy, but it’s basically just worse regardless because this thing has cracked the code.

Adaptability is beaten by perfect strategic play in games with clear victory conditions.

My familiarity with optimal control theory is nil but Kydland (1977) applied it to monetary policy to show that the right rules dominate discretion. What the right rules are for monetary policy is still an open question though, because while the victory conditions in economic policy are clearly defined the surrounding environment is very far from static so you deal with out of training set data regularly. Once AI can deal with these kind of out of context problems it seems plausible GAI is a matter of time.

http://www.finnkydland.com/papers/Rules%20Rather%20than%20Di...

> Rules Rather than Discretion: The Inconsistency of Optimal Plans

> Even if there is an agreed-upon, fixed social objective function and policymakers know the timing and magnitude of the effects of their actions, discretionary policy, namely, the selection of that decision which is best, given the current situation and a correct evaluation of the end- of-period position, does not result in the social objective function being maximized. The reason for this apparent paradox is that economic planning is not a game against nature but, rather, a game against rational economic agents. We conclude that there is no way control theory can be made applicable to economic planning when expectations are rational.

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

#240

Post by solidasparagus »

noambrown wrote: post #233
solidasparagus wrote: post #213

So Dota 2 doesn't count as a multiplayer game? OpenAI Five beat the world champions in back-to-back games...

From an AI and game theory standpoint, there isn't much difference between two-team zero-sum and two-player zero-sum if the teammates are trained together. That said, the Dota 2 work is extremely impressive for a variety of other reasons.

There is far more ambiguity when you are competing against five mostly-aligned strategies vs a single shared strategy.
Post reply on HN