摘要: As computer games become more complex and consumers demand sophisticated controlled agents, developers are required to place a greater emphasis on the artificial intelligence aspects of their games. One source AI techniques is research community. This paper discusses recent efforts by our group at University Michigan Artificial Intelligence Lab apply state art Our experience developing intelligent air combat agents for DARPA training exercises, described in John Laird's lecture 1998 Computer Game Developer's Conference, suggested that many principles from community applicable A project, called Soar/Games has followed up this games, including Quake II Descent 3. The result these two partially implemented design an engine based well established systems techniques.