DeepMind's MuZero teaches itself how to win at Atari, chess, shogi, and Go

In a preprint paper, researchers at Alphabet's DeepMind detail MuZero, an algorithm that effectively teaches itself how to play Atari and board games.

AlphaGo - Google DeepMind

Alphazero :: Computer-bridge1

MuZero

Algorithms, Free Full-Text

MuZero: The Walkthrough (Part 3/3), by David Foster, Applied Data Science

Supplementary information for “The AI Revolution: what it means for you”

How does the computer program AlphaZero determine which move to make in chess? Is there any insight that can be gained from looking at its strategy? - Quora

AlphaZero: Shedding new light on chess, shogi, and Go - Google DeepMind

Is it possible for machine logic to evolve? AlphaZero taught itself to play chess and demolished Stockfish, just as some AI's create language which its programmers can't understand. - Quora

How is Google's DeepMind different from already existing machine learning technologies? - Quora

MuZero figures out chess, rules and all

MuZero: Mastering Go, chess, shogi and Atari without rules - Google DeepMind

papers