MuZero
MuZero is a reinforcement learning algorithm developed by DeepMind that learns a model of an environment for planning without being given its rules or dynamics.
≈ 1 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
MuZero is a reinforcement learning algorithm developed by DeepMind that learns a model of an environment for planning without being given its rules or dynamics. It was introduced in a 2019 preliminary paper and described in a 2020 Nature paper.
MuZero was evaluated on Go, chess, shogi, and Atari games, where it achieved performance comparable to or better than previous systems in the reported experiments. MuZero was trained via self-play, with no access to rules, opening books, or endgame tablebases.
The trained algorithm used the same convolutional and residual architecture as AlphaZero, but with 20 percent fewer computation steps per node in the search tree.
Text derived from https://en.wikipedia.org/w/index.php?oldid=1377976744 under CC BY-SA 4.0; modifications have been made.