Das US-Verteidigungsministerium hat einen Zweijahresvertrag mit den Entwicklern der künstlichen Intelligenz (KI) „Libratus“ abgeschlossen. Tuomas Sandholm und seine Mitstreiter haben Details zu ihrer Poker-KI Libratus veröffentlicht, die jüngst vier Profispieler deutlich geschlagen. Im Jahr war es der KI Libratus gelungen, einen Poker-Profi bei einer Partie Texas-Hold'em ohne Limit zu schlagen. Diese Spielform gilt.
Libratus Poker Bot vernichtet menschliche Gegner – Der Anfang vom Ende?Die vorgestellten Poker-Programme Libratus (ebenfalls von Sandholm und Brown) [a] und DeepStack [b] konnten zwar erstmals. Our goal was to replicate Libratus from a article published in Science titled Superhuman AI for heads-up no-limit poker: Libratus beats top professionals. Die Mechanismen hinter dem KI-Bot, der ein Team aus Pokerpros vor knapp einem Jahr alt aussehen ließ, wurden nun in einem.
Libratus Poker From Zero to Hero in 2 Years VideoJason Les Discusses Playing AI Poker Bot Liberatus
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. May 31, View code. Deep mind pokerbot for pokerstars and partypoker This pokerbot plays automatically on Pokerstars and Partypoker.
Releases No releases published. Packages 0 No packages published. Yet Libratus is one giant poker player HUD in of itself.
It analyzed its own play and found its own holes as well as collecting stats and information on the human Poker players it played against.
Therefore Poker Huds offer an unfair advantage to those that have and use them vs. If you play poker online you may have one already.
Next time you go to reload cash in your poker account think about What I Just Said. Especially so in the shark filled waters of sites like Poker Stars.
Get Poker Tracker 4 and start using it to win, then add on to it for your niche, like sit n goes, tournaments, cash games… Do it seriously. As Libratus shows computer software analyzing play is the way to get a jump on your opponents like this computer did against the non software using human opponents.
A Nash Equilibrium is a strategy which ensures that the player who is using it will, at the very least, not fare worse than a player using any other strategy.
In layman's terms: Playing the Nash equilibrium strategy means you cannot lose against any other player in the long run.
The existence of those equilibriums was proven by John Nash in and the proof earned him the Nobel Prize in Economics.
This Nash equilibrium means: Guts, reads and intuition don't matter in the end. There is perfect strategy for poker; we just have to find it.
All you need is a suitable computer which can handle quadrillions of different situations, works on millions of billions of terabyte of memory and is blazingly fast.
Then you put a team of sharp, clever humans in front of it, let them develop a method to utilize the computational power and you're there. Right now Libratus is just the beginning.
The AI still simplifies many different poker situations. For example it might not differentiate between a king-jack high flush-draw and a king-ten high flush-draw.
But Libratus is already close to having developed a perfect strategy — at least close enough to annihilate any human counterpart.
Libratus beat humans in No-Limit Heads-Up. Two years ago the University of Alberta introduced Cepheus to the world -- a bot which, for all intents and purposes, plays a perfect Limit Heads-Up strategy.
It's safe to say that those two variants are practically solved. As a matter of fact the guys from the University of Alberta managed to prove that their bot is at worst 0.
Nash equilibrium strategy. While The No-Limit bot Libratus might be much further away from this perfect strategy, it's only a matter of time before it'll be refined and get closer to it.
What about other poker variants? Poker with more than two players is orders of magnitudes more complex than heads-up.
The same holds true for more difficult variants like Omaha. But a bot like Libratus is still so complex it requires a direct connection to its enormous super computer while playing.
And it still plays remarkably slow. So there's no direct danger of it being used in your local casino or online game.
The scary fact is: Bots don't even have to play a perfect strategy. An information set is a collection of game states that a player cannot distinguish between when making decisions, so by definition a player must have the same strategy among states within each information set.
Thus, imperfect information makes a crucial difference in the decision-making process. To decide their next action, player 2 needs to evaluate the possibility of all possible underlying states which means all possible hands of player 1.
Because the player 1 is making decisions as well, if player 2 changes strategy, player 1 may change as well, and player 2 needs to update their beliefs about what player 1 would do.
Heads up means that there are only two players playing against each other, making the game a two-player zero sum game. No-limit means that there are no restrictions on the bets you are allowed to make, meaning that the number of possible actions is enormous.
In contrast, limit poker forces players to bet in fixed increments and was solved in . Nevertheless, it is quite costly and wasteful to construct a new betting strategy for a single-dollar difference in the bet.
Libratus abstracts the game state by grouping the bets and other similar actions using an abstraction called a blueprint.
In a blueprint, similar bets are be treated as the same and so are similar card combinations e. Ace and 6 vs.
Ace and 5. The blueprint is orders of magnitude smaller than the possible number of states in a game.
Libratus solves the blueprint using counterfactual regret minimization CFR , an iterative, linear time algorithm that solves for Nash equilibria in extensive form games.
Libratus uses a Monte Carlo-based variant that samples the game tree to get an approximate return for the subgame rather than enumerating every leaf node of the game tree.
It expands the game tree in real time and solves that subgame, going off the blueprint if the search finds a better action.
Solving the subgame is more difficult than it may appear at first since different subtrees in the game state are not independent in an imperfect information game, preventing the subgame from being solved in isolation.
This decouples the problem and allows one to compute a best strategy for the subgame independently. In short, this ensures that for any possible situation, the opponent is no better-off reaching the subgame after the new strategy is computed.
Thus, it is guaranteed that the new strategy is no worse than the current strategy. This approach, if implemented naively, while indeed "safe", turns out to be too conservative and prevents the agent from finding better strategies.
The new method  is able to find better strategies and won the best paper award of NIPS From Wikipedia, the free encyclopedia. Artificial intelligence poker playing computer program.
IEEE Spectrum. Retrieved Artificial Intelligence". Carnegie Mellon University. MIT Technology Review. Interesting Engineering.