Slashdot Mirror
The State of AI In Games
CowboyRobot writes "Carnegie Mellon researcher Alexander Nareyek has an article at ACM Queue describing how the role of graphics as the leading technology in gaming is being replaced by advancements in artificial intelligence. The author targets some game AI: 'Early milestone demonstrations for the publisher, press presentations, and other hype-generating events do not promote inclusion of a globally/consistently good AI, but instead focus on one or two 'absolutely unexpected but genius outcomes of revolutionary new and complex AI procedures' (did you spot the ironic tone?) that provide the necessary 'wows'.' He concludes by suggesting: 'we need to see more effort to make AI functionality available for the designers/artists.'"
It has always been my dream to be playing a game and not know whether I was playing a person or a machine in any given match.
When I sat down to make my own game however that got tossed out the window. It's so much easier to write decent net code then a decent A.I. that the two can't be compared, and when you consider that A.I. will never offer the same level of intensity that another player will the choice is obvious.
Assuming that game developers are failing in the development of decent A.I. is besides the point, the real problem involves a total lack of motivation.
For example it's easy to accheieve play balance with two people who use the same race and have the same variables applied, the more diffrences you create the more problems arise.