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

Julian Schrittwieser and colleagues submitted the paper Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model to arXiv on November 19, 2019. The paper presents the MuZero algorithm, which combines tree-based search with a learned model and reports results across Atari, Go, chess, and shogi without being given the underlying environment dynamics or game rules.