用三维注意力机制提升实时战略游戏局势评估精度
Three-dimensional attention Transformer for state evaluation in real-time strategy games
- 设计空间-时间-特征三重注意力模块，分层建模战场信息
- 早期游戏阶段准确率达58.7%，中期达97.6%，波动极小
- 参数更少（475万），适合实时决策场景
实时战略游戏中的局势评估对理解复杂对抗环境下的决策至关重要。现有方法在处理多维特征信息和时序依赖方面仍存局限。本文提出一种三重空间-时间-特征注意力变压器（TSTF Transformer）架构，通过三个独立但级联的模块——空间注意力、时间注意力和特征注意力——高效建模战场态势。在包含3,150场对抗实验的数据集上，8层TSTF Transformer表现优异：早期游戏阶段（约4%进度）准确率达58.7%，显著优于传统Timesformer的41.8%；中期游戏阶段（约40%进度）准确率达97.6%，且性能波动极小（标准差0.114）。该架构参数量仅为475万，低于基线模型的554万。本研究不仅为RTS游戏局势评估提供新视角，也提出了基于Transformer的多维时序建模新范式。
原文摘要 · Abstract (English)
Situation assessment in Real-Time Strategy (RTS) games is crucial for understanding decision-making in complex adversarial environments. However, existing methods remain limited in processing multi-dimensional feature information and temporal dependencies. Here we propose a tri-dimensional Space-Time-Feature Transformer (TSTF Transformer) architecture, which efficiently models battlefield situations through three independent but cascaded modules: spatial attention, temporal attention, and feature attention. On a dataset comprising 3,150 adversarial experiments, the 8-layer TSTF Transformer demonstrates superior performance: achieving 58.7% accuracy in the early game (~4% progress), significantly outperforming the conventional Timesformer's 41.8%; reaching 97.6% accuracy in the mid-game (~40% progress) while maintaining low performance variation (standard deviation 0.114). Meanwhile, this architecture requires fewer parameters (4.75M) compared to the baseline model (5.54M). Our study not only provides new insights into situation assessment in RTS games but also presents an innovative paradigm for Transformer-based multi-dimensional temporal modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。