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.

DeepMind just taught AI how to win a game without knowing the rules

Mastering Atari, Go, chess and shogi by planning with a learned model

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

DeepMind's AI agent MuZero could turbocharge - BBC News

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

Want to Know the AI Lingo? Learn the Basics, From NLP to Neural Networks - WSJ

papers

MuZero - Wikipedia

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

Student of Games: DeepMind AI can beat top humans at chess, Go and poker

MuZero - Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model