PAWN: Piece Value Analysis with Neural Networks

TL;DR

This paper introduces PAWN, a neural network approach that predicts chess piece values more accurately by incorporating full board context through latent representations, outperforming previous models.

Contribution

The paper presents a novel method using CNN-based autoencoders to encode full board state, significantly improving piece value prediction accuracy over prior context-independent models.

Findings

Reduced validation mean absolute error by 16%

Predicted relative piece value within approximately 0.65 pawns

Demonstrated the importance of full state encoding for accurate predictions

Abstract

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.