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.

翻译：尽管Transformer已被公认为人工智能（AI）的多功能工具，但在国际象棋这一经典AI基准测试中，一个尚未探索的挑战随之出现。在此背景下，将视觉Transformer（ViT）融入AlphaZero不足以实现国际象棋的精通，这主要归因于ViT的计算限制。通过结合MobileNet与NextViT以优化其效率的尝试，使性能超越AlphaZero约30 Elo分。然而，我们提出了一种实用的改进方案，涉及对输入表征和价值损失函数进行简单调整。因此，我们实现了高达180 Elo分的显著性能提升，超越了当前AlphaZero在国际象棋中的最佳表现。除了这些改进，我们使用积分梯度技术获得的实验结果证实了新引入特征的有效性。