這是一個更一般性的演算法,可以同時駕馭 perfect information 與 imperfect information:
We introduce Player of Games, a general-purpose algorithm that unifies previous approaches, combining guided search, self-play learning, and game-theoretic reasoning. Player of Games is the first algorithm to achieve strong empirical performance in large perfect and imperfect information games -- an important step towards truly general algorithms for arbitrary environments.
論文裡面也提到以前的各種演算法 (包含 DeepMind 自家的一些演算法)。在 perfect information 的例子來說,可以看到沒有 AlphaZero 強 (西洋棋與圍棋),但也已經有一定水準了,算是個起頭的感覺:
This tool provides analysis of 6,000 of the most popular opening sequences from the recent history of Go, using data from 231,000 human games and 75 games AlphaGo played against human players.
Explore the board and learn how AlphaGo's moves compare to those of professional and amateur players.
Linux users have access to both NPAPI and PPAPI versions of Flash Player. However, for the last four years, the NPAPI version has been held at 11.2 and regularly updated with only security fixes while the PPAPI version (used in Chrome and Chromium based browsers), is in line with the standard Windows and Mac releases.
然後決定加碼讓兩邊同步:
Today we are updating the beta channel with Linux NPAPI Flash Player by moving it forward and in sync with the modern release branch (currently version 23). We have done this significant change to improve security and provide additional mitigation to the Linux community.