Learning Human-Like Opponent Behavior for Interactive Computer Games
Learning Human-Like Opponent Behavior for Interactive Computer Games
复制标题
学习交互式电脑游戏的类人对手行为
DOI：
10.1007/978-3-540-45243-0_20
复制
发表时间：
2003
期刊：
影响因子：
--
通讯作者：
G. Sagerer
中科院分区：
文献类型：
--
作者：
C. Bauckhage;Christian Thurau;G. Sagerer
与20世纪70年代早期的祖先相比，当今的计算机游戏具有令人难以置信的复杂性，并显示出出色的图形性能。然而，在编程智能对手时，游戏行业仍然应用大约30年前开发的技术。在本文中，我们研究对手编程是否可以被视为一个问题的行为学习。为此，我们假设游戏角色的行为是一个将当前游戏状态映射到反应上的函数。我们将展示神经网络架构非常适合学习这些功能，并通过一个流行的商业游戏，我们证明了代理行为可以从观察中学习。
Compared to their ancestors in the early 1970s, present day computer games are of incredible complexity and show magnificent graphical performance. However, in programming intelligent opponents, the game industry still applies techniques developed some 30 years ago. In this paper, we investigate whether opponent programming can be treated as a problem of behavior learning. To this end, we assume the behavior of game characters to be a function that maps the current game state onto a reaction. We will show that neural networks architectures are well suited to leam such functions and by means of a popular commercial game we demonstrate that agent behaviors can be learned from observation.