The Leela Chess Zero policy network encodes information about destination squares of moves up to seven plies ahead, with attention heads that copy future-square information backward in time in a pattern-dependent way.
Representation Matters for Mastering Chess: Improved Feature Representation in AlphaZero Outperforms Switching to Transformers
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
While transformers have gained recognition as a versatile tool for artificial intelligence (AI), an unexplored challenge arises in the context of chess - a classical AI benchmark. Here, incorporating Vision Transformers (ViTs) into AlphaZero is insufficient for chess mastery, mainly due to ViTs' computational limitations. The attempt to optimize their efficiency by combining MobileNet and NextViT outperformed AlphaZero by about 30 Elo. However, we propose a practical improvement that involves a simple change in the input representation and value loss functions. As a result, we achieve a significant performance boost of up to 180 Elo points beyond what is currently achievable with AlphaZero in chess. In addition to these improvements, our experimental results using the Integrated Gradient technique confirm the effectiveness of the newly introduced features.
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding the learned look-ahead behavior of chess neural networks
The Leela Chess Zero policy network encodes information about destination squares of moves up to seven plies ahead, with attention heads that copy future-square information backward in time in a pattern-dependent way.