A data mining approach to strategy prediction
A data mining approach to strategy prediction
复制标题
DOI：
10.1109/cig.2009.5286483
复制
发表时间：
2009-09
期刊：
影响因子：
--
通讯作者：
B. Weber;Michael Mateas
中科院分区：
文献类型：
--
作者：
B. Weber;Michael Mateas
我们提出了一种在策略游戏中进行对手建模的数据挖掘方法。通过将机器学习技术应用于大量游戏日志来学习专家游戏玩法。这种方法使领域无关的算法能够获取领域知识并执行对手建模。机器学习算法应用于在执行对手策略之前检测对手的策略并预测对手何时执行策略行动的任务。我们的方法涉及将游戏日志编码为特征向量表示，其中每个特征描述了单元或建筑类型首次生成的时间。我们将我们的表示与完美和不完美信息环境中的状态格表示进行比较，结果表明我们的表示具有更高的预测能力并且对噪声的容忍度更高。我们还讨论了如何将我们的数据挖掘方法合并到完整的游戏代理中。
We present a data mining approach to opponent modeling in strategy games. Expert gameplay is learned by applying machine learning techniques to large collections of game logs. This approach enables domain independent algorithms to acquire domain knowledge and perform opponent modeling. Machine learning algorithms are applied to the task of detecting an opponent's strategy before it is executed and predicting when an opponent will perform strategic actions. Our approach involves encoding game logs as a feature vector representation, where each feature describes when a unit or building type is first produced. We compare our representation to a state lattice representation in perfect and imperfect information environments and the results show that our representation has higher predictive capabilities and is more tolerant of noise. We also discuss how to incorporate our data mining approach into a full game playing agent.