Translate

sabato 4 febbraio 2017

# s-ai: handling imperfect information (from scratch), by Libratus

<< As the great Kenny Rogers once said, a good gambler has to know when to hold ’em and know when to fold ’em. At the Rivers Casino in Pittsburgh this week, a computer program called Libratus may finally prove that computers can do this better than any human card player >>

<< Libratus was created by Tuomas Sandholm, a professor in the computer science department at CMU, and his graduate student Noam Brown >>

<< Playing poker involves dealing with imperfect information, which makes the game very complex, and more like many real-world situations >>

<< Poker has been one of the hardest games for AI to crack (..)   There is no single optimal move, but instead an AI player has to randomize its actions so as to make opponents uncertain when it is bluffing >> Andrew Ng

Will Knight. Why Poker Is a Big Deal for Artificial Intelligence. Jan. 23, 2017

https://www.technologyreview.com/s/603385/why-poker-is-a-big-deal-for-artificial-intelligence/

<< Libratus, for one, did not use neural networks. Mainly, it relied on a form of AI known as reinforcement learning , a method of extreme trial-and-error. In essence, it played game after game against itself >>

<< By contrast [GO], Libratus learned from scratch.

Cade Metz. Inside Libratus, the Poker AI That Out-Bluffed the Best Humans. Feb.01, 2017 07:00 am

https://www.wired.com/2017/02/libratus/

more:

NoamBrown, Tuomas Sandholm. Safe and Nested Endgame Solving for Imperfect-Information Games.

http://www.cs.cmu.edu/~noamb/papers/17-AAAI-Refinement.pdf

Nessun commento:

Posta un commento