Acquisition of Chess Knowledge in AlphaZero

Researchers at DeepMind and Google Brain, in collaboration with Grandmaster Vladimir Kramnik, are working to explore what chess can teach us about AI and vice versa. Using Chessbase’s extensive historical chess data along with the AlphaZero neural network chess engine and components from Stockfish 8, they ask: what can we learn about chess history by studying AlphaZero, how does AlphaZero learn to evaluate positions, and is AlphaZero computing anything human-like? Their paper, “Acquisition of Chess Knowledge in AlphaZero”, has just been published.

Acquisition of chess knowledge in AlphaZero

Acquisition of chess knowledge in AlphaZero

Acquisition of Chess Knowledge in AlphaZero

Neural Networks - Chessprogramming wiki

GitHub - Nicolas-Maurer/Onitama_AlphaZero: Implementation of the AlphaZero algorithm for the game Onitama

Has every possible game of chess been played by now? - Quora

Checkmate: how we mastered the AlphaZero cover, Science

Game Of Chess: Models, code, and papers - CatalyzeX

PDF] Acquisition of chess knowledge in AlphaZero

Plane representation of an exemplary game position of our test data

Reimagining Chess with AlphaZero, February 2022

Acquisition of Chess Knowledge in AlphaZero – arXiv Vanity

Acquisition of chess knowledge in AlphaZero