Libratus Poker

This equates to a win rate of All four human players lost over their 30, hands against Libratus. This is how they performed individually:. While the rules of the challenge were set to reduce the luck factor as much as possible, chance still plays a big role in the results of each hand — even with mirrored hands and even with the elimination of all-in luck.

So maybe, just maybe, the human players are actually better but the AI just got lucky. Let's look at some statistics regarding the results.

The AI won with a win rate of Those are just rough estimates for the variance, but as we'll see they're good enough boundaries. What's the probability of the humans actually playing better than the AI but losing at a rate of It turns out this probability is very low: Somewhere between 0.

Meaning: It's very, very unlikely the general result of this challenge — the AI plays better than four humans — is due to the AI just getting lucky.

No bad luck. Basically the Libratus AI is just a huge set of strategies which define how to play in a certain situation.

Two examples of such strategies not necessarily related to the actual game play of Libratus :. It quickly becomes obvious that there are almost uncountably many different situations the AI can be in and for each and every situation the AI has a strategy.

The AI effectively rolls a dice to decide what to do but the probabilities and actions are pre-calculated and well balanced.

The computer played for many days against itself, accumulating billions, probably trillions of hands and tried randomly all kinds of different strategies.

Whenever a strategy worked, the likelihood to play this strategy increased; whenever a strategy didn't work, the likelihood decreased.

Basically, generating the strategies was a colossal trial and error run. Prior to this competition, it had only played poker against itself.

It did not learn its strategy from human hand histories. Libratus was well prepared for the challenge but the learning didn't stop there. Each day after the matches against its human counterparts it adjusted its strategies to exploit any weaknesses it found in the human strategies, increasing its leverage.

How can a computer beat seemingly strong poker players? Their new method gets rid of the prior de facto standard in Poker programming, called "action mapping".

As Libratus plays only against one other human or computer player, the special 'heads up' rules for two-player Texas hold 'em are enforced.

To manage the extra volume, the duration of the tournament was increased from 13 to 20 days. The four players were grouped into two subteams of two players each.

One of the subteams was playing in the open, while the other subteam was located in a separate room nicknamed 'The Dungeon' where no mobile phones or other external communications were allowed.

The Dungeon subteam got the same sequence of cards as was being dealt in the open, except that the sides were switched: The Dungeon humans got the cards that the AI got in the open and vice versa.

This setup was intended to nullify the effect of card luck. As written in the tournament rules in advance, the AI itself did not receive prize money even though it won the tournament against the human team.

The official competition between human and machine took place over three weeks, but it was clear that the computer was king after only a few days of play.

Libratus eventually won [1] by a staggering Libratus is not the only game-playing AI to make recent news headlines, but it is uniquely impressive.

A Deep Q-network learns how to play under the reinforcement learning framework, where a single agent interacts with a fixed environment, possibly with imperfect information.

Also in , DeepMind's AlphaGo used similar deep reinforcement learning techniques to beat professionals at Go for the first time in history.

Go is the opposite of Atari games to some extent: while the game has perfect information , the challenge comes from the strategic interaction of multiple agents.

Libratus, on the other hand, is designed to operate in a scenario where multiple decision makers compete under imperfect information.

This makes it unique: poker is harder than games like chess and Go because of the imperfect information available.

At the same time, it's harder than other imperfect information games, like Atari games, because of the complex strategic interactions involved in multi-agent competition.

In Atari games, there may be a fixed strategy to "beat" the game, but as we'll discuss later, there is no fixed strategy to "beat" an opponent at poker.

This combined uncertainty in poker has historically been challenging for AI algorithms to deal with. That is, until Libratus came along.

Libratus used a game-theoretic approach to deal with the unique combination of multiple agents and imperfect information, and it explicitly considers the fact that a poker game involves both parties trying to maximize their own interests.

The poker variant that Libratus can play, no-limit heads up Texas Hold'em poker, is an extensive-form imperfect-information zero-sum game. We will first briefly introduce these concepts from game theory.

For our purposes, we will start with the normal form definition of a game. The game concludes after a single turn. These games are called normal form because they only involve a single action.

An extensive form game , like poker, consists of multiple turns. Before we delve into that, we need to first have a notion of a good strategy.

Multi-agent systems are far more complex than single-agent games. To account for this, mathematicians use the concept of the Nash equilibrium.

Photo Copyright: rf. Feelings Will be hurt yet again in human kinds battle against the virtual minds of computers in yet another sport to fall.

Win More Money Now. Get on the side of computer intelligence tools and use them to your advantage. The evidence is clear, You need a poker tracker 4 hud to win consistently if your looking to make money in online poker.

This is your chance to get your own poker bot to read the other players hands. Yup It appears so…. Libratus from its roots in Latin means to free, and in this case free us of our money.

Dismiss Join GitHub today GitHub is home to over 50 million developers working together to host and review code, manage projects, and build software together.

Sign up. GitHub is where the world builds software Millions of developers and companies build, ship, and maintain their software on GitHub — the largest and most advanced development platform in the world.

Sign up for free Dismiss. Go back. Launching Xcode If nothing happens, download Xcode and try again. Latest commit.

Git stats commits. Failed to load latest commit information. Jun 1, Jun 14, Oct 13, Major refactoring.