article1175.asp.htm

电脑游戏中的人工智能制作的文章收集。 搞游戏设计和编程的人都可以参考一下

<!--<TABLE>
	<TR>
		<TD>
			
		</TD>
		<TD>
			See Also:
		</TD>
	</TR>
	<TR>
		<TD COLSPAN=2>-->

<P ALIGN="center"><SPAN CLASS="title">Application of Genetic Programming to the "Snake Game"</SPAN>
<BR><SPAN CLASS="author">by <A HREF="mailto:[e-mail]">Tobin Ehlis</A>
<BR><A HREF="javascript:if(confirm('http://www.rexall.com/tobin  \n\n这个文件不能通过 Teleport Pro 取回, 因为 它被访问于一个域或在它的起始地址边界外部的路径上.  \n\n你想从服务器打开它吗?'))window.location='http://www.rexall.com/tobin'" tppabs="http://www.rexall.com/tobin">http://www.rexall.com/tobin</A></SPAN>

<P><B>Abstract:</B> This paper describes the evolution of a genetic program to optimize a problem featuring task prioritization in a dynamic, randomly updated environment.  The specific problem approached is the "snake game" in which a snake confined to a rectangular board attempts to avoid the walls and its own body while eating pieces of food.  The problem is particularly interesting because as the snake eats the food, its body grows, causing the space through which the snake can navigate to become more confined.  Furthermore, with each piece of food eaten, a new piece of food is generated in a random location in the playing field, adding an element of uncertainty to the program.  This paper will focus on the development and analysis of a successful function set that will allow the evolution of a genetic program that causes the snake to eat the maximum possible pieces of food.</P>

<H1>Introduction and Overview</H1>
<P>Artificial intelligence (AI) techniques have been proven highly successful at the problems of navigation, task prioritization, and problem avoidance.  Traditionally, humans have encoded rule-based AIs to create the behaviors necessary to allow an automaton to achieve a specific task or set of tasks.  Genetic programming (GP), however, has been proven to allow a computer to create human-competitive results.  Specifically, examples such as the wall-following robot (Koza 1992) and Pac Man