Learning Chess With Language Models and Transformers
This work addresses the challenge of applying NLP to game learning, showing incremental progress in using language models for chess.
The study tackled the problem of using language models to learn board games from text-based notation, demonstrating that a BERT-based model can learn chess rules and achieve a category-A rating level against Stockfish.
Representing a board game and its positions by text-based notation enables the possibility of NLP applications. Language models, can help gain insight into a variety of interesting problems such as unsupervised learning rules of a game, detecting player behavior patterns, player attribution, and ultimately learning the game to beat state of the art. In this study, we applied BERT models, first to the simple Nim game to analyze its performance in the presence of noise in a setup of a few-shot learning architecture. We analyzed the model performance via three virtual players, namely Nim Guru, Random player, and Q-learner. In the second part, we applied the game learning language model to the chess game, and a large set of grandmaster games with exhaustive encyclopedia openings. Finally, we have shown that model practically learns the rules of the chess game and can survive games against Stockfish at a category-A rating level.