PAWN: Piece Value Analysis with Neural Networks
For chess AI and game analysis, this work improves piece value estimation by leveraging board context, though the approach is incremental.
The paper tackles the challenge of predicting the relative value of chess pieces in a position by incorporating full-board context via a CNN-based autoencoder. Their method reduces validation MAE by 16% compared to context-independent baselines, achieving prediction error of ~0.65 pawns.
Predicting the relative value of any given chess piece in a position remains an open challenge, as a piece's contribution depends on its spatial relationships with every other piece on the board. We demonstrate that incorporating the state of the full chess board via latent position representations derived using a CNN-based autoencoder significantly improves accuracy for MLP-based piece value prediction architectures. Using a dataset of over 12 million piece-value pairs gathered from Grandmaster-level games, with ground-truth labels generated by Stockfish 17, our enhanced piece value predictor significantly outperforms context-independent MLP-based systems, reducing validation mean absolute error by 16% and predicting relative piece value within approximately 0.65 pawns. More generally, our findings suggest that encoding the full problem state as context provides useful inductive bias for predicting the contribution of any individual component.