By Adrian Covert Posted 07.30.2009 at 2:35 pm 7 Comments

Ever wish you could play a game that tailors its strategy around your particular playing style? Thanks to a team of game programmers affiliated with the MIT Media Lab, and their project The Restaurant Game, that might be a reality sooner than you think.

One of the holy grails for programmers is to create artificial intelligence that's able to teach itself based on variables taken in on the fly. The Restaurant Game seeks to accomplish this by analyzing real interactions between a waiter and a customer, and figuring out which interaction combinations yield favorable results.

Related Articles

A Ground-Breaking Game
Video: Why Artificial Intelligence Threatens Actual Intelligence
The Future of Gaming

Tags

Entertainment & Gaming, Adrian Covert, artificial intelligence, games, gaming, new technology, restaurant game, videogames
The programmers, Deb Roy and Jeff Orkin, refer to these combinations as "interaction traces"; they could involve something as simple as a large tip for a promptly delivered meal. The end goal for this project is to create an AI that can adapt to different situations without the need for human programming.

And the best part is that you can help contribute to the process. The restaurant game is downloadable for OS X and Windows, and can be played through in about 10 minutes.

[via The Restaurant Game via H+ via Slashdot]

Want to read more articles like this, plus stories on gaming, music, movies, and more? Subscribe to Popular Science and enter to win $5,000!

7 Comments

link to this comment
ultimatenerd22
07/30/09 at 7:23 pm

great soon the robots will kill us all.
www.youtube.com/watch?v=hEUWrj7SyPk

link to this comment
Cuishi14

from avondale , az

07/31/09 at 5:53 pm

an AI that culd adapt to wat ur doin wuld be cool for RTS games. the enemy wuld change its stratgy based on the players stratgy.

link to this comment
thecooltodd
07/31/09 at 6:16 pm

I agree, but I'm guessing that it learns from trial and error. Once it gets adapted to one person's strategy for an RTS or even a TBS, if another person plays with a completely different style it would have to learn all over again and optimize a strategy that involves beating either player's strategy.

link to this comment
sirknala
08/03/09 at 12:59 pm

That's the point. If the game immediately knew how you played it would not be similar to a human playing the game with you. Learning how a player plays takes time no matter who you are.

link to this comment
tpel
08/04/09 at 12:27 am

skynet! here we come

link to this comment
plazzooo
09/04/09 at 10:44 am

amazing

www.tungstenplaza.com

link to this comment
uncleiroh13
09/15/09 at 7:27 pm

this is cool
--------------------------------------------------
i wish i was part of this chat about the lame macs
http://boards.ign.com/teh_vestibule/b5296/184755342/r184756381/

Popular Tags

Regular Features



Download Our iPhone App

Stay up to date on the latest news of the future of science and technology from your iPhone with full articles, images and offline viewing



Follow Us On Twitter

Featuring every article from the magazine and website, plus links from around the Web. Also see our PopSci DIY feed



Become a Fan On Facebook

Share links with friends, comment on stories and more


December 2009: Best of What's New

In our December issue, Popular Science names the 100 best innovations of the year: bombproof wallpaper, self-parking cars, the fastest helicopter, and 97 more. Plus inventor profiles and videos.

Check out the best of what's new here.

Popular Science Photo Pool


Share your photos in the Pop Sci pool at www.flickr.com!
tags_sprite.png
POP_embeddedForm_cover_May09.jpg