[Very busy at work right now, so posts will taper off until I get to the holiday at the end of the month. That said, I do have some 20+ posts drafted. Rest assured, more content is on the way.]
Being a member of the IEEE, I regularly browse the latest issue of IEEE Spectrum. The most recent issue (December 2008) includes an article entitled “Bots Get Smart” by Jonathan Schaeffer, Vadim Bulitko, and Michael Buro. The main topic of the article is the improving of game AI in order to provide better experiences for players.
One of the parts that stood out to me was this paragraph:
This project has so far produced a formal system for analyzing and classifying a team’s opening moves. That may not sound like much, but this task proved immensely challenging, because positions and actions are not nearly as constrained as they are in a game like chess. Researchers in our group have used this formalism to analyze computer logs of more than 50 hours of tournament-level play between seasoned Counter-Strike teams. Soon, we expect, computer bots programmed to learn tactics from such logs will play reasonably well—doing things a person might do. It’ll be a long time before these bots will be able to beat expert human players, though. But that’s not the objective, after all—they just need to make for entertaining adversaries.
I find this quite interesting. We’ll never see Counter-Strike being solved, but the prospect of analyzing and classifying the opening moves is intriguing.
If you follow the game AI field, you’ll probably recognize the name of primary author of this paper: Jonathan Schaeffer. If you don’t, I’ll take the opportunity to direct you to the book One Jump Ahead which is the story of Chinook, the champion computer checkers player. Actually, I’m pleasantly surprised to see that there is newly revised paperback edition that was issued last month. Presumably, it will take into account the most recent developments in the field, as the original edition of the book is from 1997.
Leave a Reply