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.

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

Computer chess - Wikipedia

DeepMind's AlphaZero beats state-of-the-art chess and shogi game engines

DeepMind's AlphaZero beats state-of-the-art chess and shogi game engines

DeepMind's MuZero conquers and learns the rules as it does

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

How does AI learn chess? - Chess Forums

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

Inside AI Companies: Top 10 Innovations by Google DeepMind So Far

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

Will AlphaZero become smarter and smarter forever, if it plays chess against itself for unlimited times? - Quora

AI, Free Full-Text

Listen to DeepMind: The Podcast podcast

DeepMind AI teaches itself chess from scratch in four hours, proceeds to beat previous champion