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

101–110 of 123 posts

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

#101

Post by andrewprock »

xapata wrote: post #95
andrewprock wrote: post #92

Earlier quoted context omitted.

There are no fundamental algorithmic differences between chess and poker. The incomplete information aspect of it only increases the size of the nodes in a game tree, as each node must now track all possible private states for each public state. Beyond that, there are no fundamental algorithmic differences. There are algorithms that have been devised to handle such large game trees to speed convergence (regret minimi…

The fundamental difference is the way poker is played repeatedly, tracking winnings over a long period. Winning a single hand is meaningless. Chess can be modeled with each game serving as a single observation. Poker must consider each player's entire lifetime as a single observation. Not simply a hand, but all hands that player has ever played, including what that player knew about all opponents ever faced. This qua…

This does not apply to solutions which are Nash equilibriums. You are discussing exploitative strategies, something which the CMU team did not attempt to create. They created a game theory optimal strategy.

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

#102

Post by andrewprock »

Jefro118 wrote: post #96
andrewprock wrote: post #93

Earlier quoted context omitted.

In no limit, if you lose a hand you have fewer chips, which changes the applicable strategy. There is no version of no limit where every hand is played with the same number of chips. It is akin to only playing the first 10 moves of a chess game, then resetting.

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.

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

#103

Post by xapata »

andrewprock wrote: post #101
xapata wrote: post #95

Earlier quoted context omitted.

The fundamental difference is the way poker is played repeatedly, tracking winnings over a long period. Winning a single hand is meaningless. Chess can be modeled with each game serving as a single observation. Poker must consider each player's entire lifetime as a single observation. Not simply a hand, but all hands that player has ever played, including what that player knew about all opponents ever faced. This qua…

This does not apply to solutions which are Nash equilibriums. You are discussing exploitative strategies, something which the CMU team did not attempt to create. They created a game theory optimal strategy.

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.

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

#104

Post by xapata »

hunl wrote: post #37
skoutus wrote: post #29

I wonder if the players tried colluding: coordinate their bets to fake a weakness so the AI start to adopt a poor strategy, then up the bets and stop the feign. I don't see how the AI can protect itself against that.

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.

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

#105

Post by cgearhart »

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…

I tend to disagree that this represents an explosion of approaches. For example, AlphaGo and DeepBlue are more similar than they may at first seem. AlphaGo used MCTS (a search algorithm), and value and policy networks as heuristics to evaluate board positions and search order. AlphaGo scored a couple of big wins by showing that you don't need exhaustive search (in fact, AlphaGo evaluates orders of magnitude fewer nodes in the game tree than previous state-of-the art MCTS Go agents, and Go is notorious for such a high branching factor that minimax, et. al., are straight out), and that the heuristic can be learned through reinforcement learning.

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

#106

Post by oculusthrift »

dgacmu wrote: post #77
smohnot wrote: post #41

Earlier quoted context omitted.

http://motherboard.vice.com/read/a-poker-playing-supercomput... Lost by $732,713, with $170 million bet... pretty close. But you're right, a victory by a chip will be declared a win

That's both an unfair slight to the ethics of the researchers involved, as well as inaccurate. They've published in advance their criteria for declaring a victory vs a tie: http://www.cardplayer.com/poker-news/21215-poker-bot-doubles... which is: "If after 120,000 hands either Libratus or the humans are one standard deviation above break-even, they will have won the competition with “statistical significance.”" (I'm…

we mostly mean by the media. Story if they barely lose "Poker bot statistically ties pros". Story if they are one chip up: "Poker bot leads/beats pros"

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

#107

Post by andrewprock »

xapata wrote: post #103
andrewprock wrote: post #101

Earlier quoted context omitted.

This does not apply to solutions which are Nash equilibriums. You are discussing exploitative strategies, something which the CMU team did not attempt to create. They created a game theory optimal strategy.

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...

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

#108

Post by andrewprock »

dgacmu wrote: post #77
smohnot wrote: post #41

Earlier quoted context omitted.

http://motherboard.vice.com/read/a-poker-playing-supercomput... Lost by $732,713, with $170 million bet... pretty close. But you're right, a victory by a chip will be declared a win

That's both an unfair slight to the ethics of the researchers involved, as well as inaccurate. They've published in advance their criteria for declaring a victory vs a tie: http://www.cardplayer.com/poker-news/21215-poker-bot-doubles... which is: "If after 120,000 hands either Libratus or the humans are one standard deviation above break-even, they will have won the competition with “statistical significance.”" (I'm…

One standard deviation is not enough to declare that one strategy is better than another.

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

#109

Post by thefalcon »

oculusthrift wrote: post #98
patrick_haply wrote: post #63

Earlier quoted context omitted.

> also important to note they made the players play thousands of hands over weeks To your point, I wonder how they account for mental and physical fatigue. To a computer it makes no difference to play thousands of hands over such a long period of time or hundreds of hands over the course of a single day. Humans on the other hand don't have the same attention span as a computer.

not to mention that people play differently with fake money than real money.

On the Twitch Stream, Jason Les "promises" that "even though this is not real money" it really matters to him.

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

#110

Post by czzarr »

tansey wrote: post #94
vannevar wrote: post #88

Earlier quoted context omitted.

Yes, I'm wondering if anyone is tracking the relative strength of each player's hands. In the end, the bot should be declared the "winner" only if its winnings were disproportionately high in relation to the strength of its hands.

The usual way they reduce variance in these man vs. machine poker showdowns is to do "pairs" play. You have two humans playing simultaneously in isolated locations. The decks for both humans are the same, but player 1 and 2 are swapped for one human. That way, the bot strategy has to play both hands. It does totally eliminate variance, but they also take that into account and correct for it when looking at final outc…

That trick doesn't change the variance at all if decks are the same.

Typical winrates in human vs human are between 1-5ptbb/100 where 1ptbb = two big blinds. At 1ptbb the variance is pretty big and north of 1million hands are probably necessary to establish an edge, whereas at 5ptbb the variance is much smaller and 100k hands are usually enough to converge to the expected value

Post reply on HN