조금 오래된 기사이긴 합니다만 Libratus 라는 AI 프로그램이 포커에서 프로 플레이어들을 이긴 것에 관한 기사입니다.

이는 기존의 체스나 바둑같이 모든 정보가 주어진 상황이 아니라 블러핑과 같은 심리전이 존재하는 경우에서도 AI 의 성능이 사람과 동등하거나 이상의 퍼포먼스를 보여준 것으로 볼 수 있습니다.

작동하는 방식은 세단계로 나누어 보면 아래와 같습니다.
  • First, the AI’s algorithms computed a strategy before the tournament by running for 15 million processor-core hours on a new supercomputer called Bridges. 
  • Second, the AI would perform “end-game solving” during each hand to precisely calculate how much it could afford to risk in the third and fourth betting rounds (the “turn” and “river” rounds in poker parlance). Sandholm credits the end-game solver algorithms as contributing the most to the AI victory. The poker pros noticed Libratus taking longer to compute during these rounds and realized that the AI was especially dangerous in the final rounds, but their “bet big early” counter strategy was ineffective.
  • Third, Libratus ran background computations during each night of the tournament so that it could fix holes in its overall strategy. That meant Libratus was steadily improving its overall level of play and minimizing the ways that its human opponents could exploit its mistakes. It even prioritized fixes based on whether or not its human opponents had noticed and exploited those holes. By comparison, the human poker pros were able to consistently exploit strategic holes in the 2015 tournament against the predecessor AI called Claudico.
기사 원문
https://spectrum.ieee.org/automaton/robotics/artificial-intelligence/ai-learns-from-mistakes-to-defeat-human-poker-players
http://www.independent.co.uk/life-style/gadgets-and-tech/news/ai-poker-win-tournament-software-beats-pro-players-victory-a7555791.html
profile