Chess is a two-player strategy board game played on a chessboard, a checkered gameboard with 64 squares arranged in an 8×8 grid. The idea of making a machine that could beat a Grandmaster human player was a fascination in the artificial community for decades. Famously IBM's DeepBlue beat Kasparov in the 1990s. More recently more human-like approaches such as AlphaZero have appeared.
When evaluated on Go, chess and shogi, without any knowledge of the game rules, MuZero matched the superhuman performance of the AlphaZero algorithm that was supplied with the game rules.
SOTA for Atari Games on Atari 2600 Robotank
This report presents Giraffe, a chess engine that uses self-play to discover all its domain-specific knowledge, with minimal hand-crafted knowledge given by the programmer.
We present an end-to-end learning method for chess, relying on deep neural networks.