Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ye, Yanqing, Yang, Weilong, Qiu, Kai, Zhang, Jie
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2501.03832
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912179288014848
author Ye, Yanqing
Yang, Weilong
Qiu, Kai
Zhang, Jie
author_facet Ye, Yanqing
Yang, Weilong
Qiu, Kai
Zhang, Jie
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_03832
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Three-dimensional attention Transformer for state evaluation in real-time strategy games
Ye, Yanqing
Yang, Weilong
Qiu, Kai
Zhang, Jie
Machine Learning
Artificial Intelligence
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.
title Three-dimensional attention Transformer for state evaluation in real-time strategy games
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2501.03832