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

CMU's Libratus builds substantial lead in Brains vs. AI competition

cmu.edu

Post reply on HN
Print view View original

111–120 of 123 posts

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#111

Post by hunl »

xapata wrote: post #104
hunl wrote: post #37

Earlier quoted context omitted.

The aim of the AI isn't to adopt to poor strategies, rather to play an approximate optimal strategy itself. It's aiming to be unexploitable, the further the other players deviate from optimal, the more it wins. It's EV (expected value) comes from the other players not playing optimally, it doesn't care about exploiting individual weaknesses.

Then I'd say it's not a very good poker player.

If you define a 'not very good' strategy as losing at a maximum of 0, then sure. Playing optimally means the worst case scenario against any opponent would be breaking even. It doesn't have to be trained on individual playing styles, it is simply playing each spot theoretically correctly.

An example, say the humans are getting to a river situation with too many bluffs for a given betsize, an exploit for the AI would be to always call. The opposite is also true, if they are bluffing too little it should always fold. The players notice that the AI has adjusted, and adjust their frequencies - now exploiting the AI. By taking an exploitative approach the AI leaves itself open to be exploited, this is not the goal.

If this were rock paper scissors, the AI is doing the equivalent of always throwing each at 1/3 - even when it's opponent throws rock every time. It could switch to paper, but a thinking opponent will now switch to scissors, this will continue until we are back at equilibrium. The AI aims to play poker in this same fashion, having the correct frequencies of actions for a given range in every spot.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#112

Post by poikniok »

andrewprock wrote: post #102
Jefro118 wrote: post #96

Earlier quoted context omitted.

This is indeed a version of no limit. What defines it as no limit is that there is "no limit" on the bet sizes. The fact that the chips are reset each hand doesn't mean it isn't no limit. The chess analogy would be more akin to resetting after the flop.

On the contrary, no limit is never played where you reset the game after every hand. The fact that this is happening indicates that the strategy is not in fact complete. I expect the strategy would lose a heads up tournament nearly every time.

I am pretty sure you are trying to level people, nobody can misunderstand a simple concept to this extent.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#113

Post by xapata »

hunl wrote: post #111
xapata wrote: post #104

Earlier quoted context omitted.

Then I'd say it's not a very good poker player.

If you define a 'not very good' strategy as losing at a maximum of 0, then sure. Playing optimally means the worst case scenario against any opponent would be breaking even. It doesn't have to be trained on individual playing styles, it is simply playing each spot theoretically correctly. An example, say the humans are getting to a river situation with too many bluffs for a given betsize, an exploit for the AI would…

A better AI should be able to fool the opponent into thinking it has thrown rock (metaphorically) so that the opponent throws paper while the AI instead throws scissors.

Poker isn't about equilibrium, it's about misdirection and exploitation. When the table gets cold, you liven it up by convincing everyone to do a round of straddle.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#114

Post by xapata »

andrewprock wrote: post #107
xapata wrote: post #103

Earlier quoted context omitted.

Optimal strategy might not be a Nash equilibrium. I'm not sure why you think game theory ignores that possibility. The Alberta team wrote some good papers about it.

In a two player no-limit hold'em game, a game theory optimal solution will be at a Nash equilibrium. see: https://en.wikipedia.org/wiki/Nash_equilibrium#Nash.27s_Exis...

You misunderstood "a solution" to mean the only optimal solution. Also, note that Nash equilibrium assumes the opponent does not change strategy. Once you relax that assumption, especially with the idea that you can induce change, another strategy becomes viable.

Check out the "Occurrence" section in the article you linked to.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#115

Post by andrewprock »

poikniok wrote: post #112
andrewprock wrote: post #102

Earlier quoted context omitted.

On the contrary, no limit is never played where you reset the game after every hand. The fact that this is happening indicates that the strategy is not in fact complete. I expect the strategy would lose a heads up tournament nearly every time.

I am pretty sure you are trying to level people, nobody can misunderstand a simple concept to this extent.

Not at all. Their strategy has almost no practical level in any existing poker game. They've come up with a solution to a variant of poker that no one actually plays.

It's a great solution, and at that stack size, I'm sure it's better than nearly every human competitor. But until they solve all stack sizes down to one big blind, their strategy is practically incomplete.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#116

Post by poikniok »

andrewprock wrote: post #115
poikniok wrote: post #112

Earlier quoted context omitted.

I am pretty sure you are trying to level people, nobody can misunderstand a simple concept to this extent.

Not at all. Their strategy has almost no practical level in any existing poker game. They've come up with a solution to a variant of poker that no one actually plays. It's a great solution, and at that stack size, I'm sure it's better than nearly every human competitor. But until they solve all stack sizes down to one big blind, their strategy is practically incomplete.

You do realize that the deeper the effective stacks are the harder the game is to solve? It is far easier to approach GTO the closer we get to push fold games, and thus your suggestion is akin to acknowledging that they have landed on the moon, but how about they climb this tree over here. If your username suggests you are who you are, this is a bit bizarre to me that an apparently intelligent engineering manager who has played poker before can be so woefully misinformed. If you want to learn more I suggest posting your thoughts on 2+2, they will gladly explain why your thesis makes no sense.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#117

Post by hunl »

xapata wrote: post #113
hunl wrote: post #111

Earlier quoted context omitted.

If you define a 'not very good' strategy as losing at a maximum of 0, then sure. Playing optimally means the worst case scenario against any opponent would be breaking even. It doesn't have to be trained on individual playing styles, it is simply playing each spot theoretically correctly. An example, say the humans are getting to a river situation with too many bluffs for a given betsize, an exploit for the AI would…

A better AI should be able to fool the opponent into thinking it has thrown rock (metaphorically) so that the opponent throws paper while the AI instead throws scissors. Poker isn't about equilibrium, it's about misdirection and exploitation. When the table gets cold, you liven it up by convincing everyone to do a round of straddle.

Heads up poker is precisely about equilibrium. Your straddle reference is also irrelevant, this is not live multiway poker.

"Tricking an opponent into thinking it has metaphorically thrown rock" extrapolated into a poker example would be betting larger/smaller, calling more/less, folding more/less than is optimal in a given scenario in the hope that your opponent makes a (bigger) mistake. You're simply hoping he makes more errors than you, the AI instead choses to just make zero mistakes and let the opponents do the rest. You can see this in action for yourself in Heads up limit holdem by playing Cepheus (http://poker-play.srv.ualberta.ca)

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#118

Post by andrewprock »

xapata wrote: post #114
andrewprock wrote: post #107

Earlier quoted context omitted.

In a two player no-limit hold'em game, a game theory optimal solution will be at a Nash equilibrium. see: https://en.wikipedia.org/wiki/Nash_equilibrium#Nash.27s_Exis...

You misunderstood "a solution" to mean the only optimal solution. Also, note that Nash equilibrium assumes the opponent does not change strategy. Once you relax that assumption, especially with the idea that you can induce change , another strategy becomes viable. Check out the "Occurrence" section in the article you linked to.

A Nash equilibrium strategy does not assume that an opponents strategy never changes. A Nash equilibrium has the property that if the opponents strategy deviates from a Nash equilibrium, then the opponent will lose.

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#119

Post by nopinsight »

nopinsight wrote: post #31

I believe we are witnessing the Cambrian explosion of intelligences. The techniques behind Libratus (abstraction algorithm and game theory [1]) appear to be qualitatively distinct from those behind AlphaGo (deep reinforcement learning and MCMC) and DeepBlue (search and heuristics). An ecology of Artificial Intelligences, unbounded by our evolutionary history and neural architecture, could evolve to suit each particul…

Correction: One of AlphaGo's techniques is MCTS (Monte Carlo Tree Search), not MCMC (Markov Chain Monte Carlo).

Re: CMU's Libratus builds substantial lead in Brains vs. AI competition

#120

Post by andrewprock »

poikniok wrote: post #116
andrewprock wrote: post #115

Earlier quoted context omitted.

Not at all. Their strategy has almost no practical level in any existing poker game. They've come up with a solution to a variant of poker that no one actually plays. It's a great solution, and at that stack size, I'm sure it's better than nearly every human competitor. But until they solve all stack sizes down to one big blind, their strategy is practically incomplete.

You do realize that the deeper the effective stacks are the harder the game is to solve? It is far easier to approach GTO the closer we get to push fold games, and thus your suggestion is akin to acknowledging that they have landed on the moon, but how about they climb this tree over here. If your username suggests you are who you are, this is a bit bizarre to me that an apparently intelligent engineering manager who…

Yes, I am who I am, and I've done a little more than "play poker before".

While it is true that solving a smaller stack size is cheaper, you have to solve many stack sizes from 1 to N to get good coverage across the space of all play.

I've been following this work for over 15 years, and they certainly deserve credit for what they did. But what they have done falls short of the banner headline.

Post reply on HN