Building a player strategy model by analyzing replays of real-time strategy games

Ji Lung Hsieh*, Chuen-Tsai Sun

*此作品的通信作者

研究成果: Conference contribution同行評審

81 引文 斯高帕斯(Scopus)

摘要

Developing computer-controlled groups to engage in combat, control the use of limited resources, and create units and buildings in Real-Time Strategy(RTS) Games is a novel application in game AI. However, tightly controlled online commercial game pose challenges to researchers interested in observing player activities, constructing player strategy models, and developing practical AI technology in them. Instead of setting up new programming environments or building a large amount of agent's decision rules by player's experience for conducting real-time AI research, the authors use replays of the commercial RTS game StarCraft to evaluate human player behaviors and to construct an intelligent system to learn human-like decisions and behaviors. A case-based reasoning approach was applied for the purpose of training our system to learn and predict player strategies. Our analysis indicates that the proposed system is capable of learning and predicting individual player strategies, and that players provide evidence of their personal characteristics through their building construction order.

原文English
主出版物標題2008 International Joint Conference on Neural Networks, IJCNN 2008
頁面3106-3111
頁數6
DOIs
出版狀態Published - 2008
事件2008 International Joint Conference on Neural Networks, IJCNN 2008 - Hong Kong, China
持續時間: 1 6月 20088 6月 2008

出版系列

名字Proceedings of the International Joint Conference on Neural Networks

Conference

Conference2008 International Joint Conference on Neural Networks, IJCNN 2008
國家/地區China
城市Hong Kong
期間1/06/088/06/08

指紋

深入研究「Building a player strategy model by analyzing replays of real-time strategy games」主題。共同形成了獨特的指紋。

引用此