TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Computer Learns Game by Reading Manual

40 pointsby abrenzelalmost 14 years ago

8 comments

noonatalmost 14 years ago
The article is sparse on details, but the linked MIT news article goes into more depth. Of note, the algorithm was able to win 79% of the games it played. Without textual input, it only won 46%, and a more advanced machine learning algorithm without textual input only won 62%. Pretty cool.
评论 #2760827 未加载
评论 #2761219 未加载
Shenglongalmost 14 years ago
It can read <i>and</i> apply what it's read? This program is already more advanced than half my graduating high school class.
cgs1019almost 14 years ago
Two things come to my mind:<p>1. That's gotta be one helluva manual<p>2. Reversing the procedure to automate documentation by examining variable and method names along various code paths would be brilliant.
nateberkopecalmost 14 years ago
Good thing we're teaching them Civilization - they'll never get out of the server room.<p>Teaching ultra-intelligent AI Monopoly, though? - guaranteed robot overlords.
评论 #2760217 未加载
评论 #2760184 未加载
malvosenioralmost 14 years ago
Does that mean if the program read additional texts on Civilization strategy that it would get even better? How about texts that may be somewhat related but not specific to the game (combat strategy, world history?!...)
评论 #2761047 未加载
dlwhalmost 14 years ago
I'm somewhat familiar with this work. (My advisor talked to the authors some. I could be misrepresenting it a little, but not nearly as much as the article.)<p>It's not learning to play the whole game. It's learning to cheese (in gaming parlance) the opponent. The strategy it learns is to build a warrior as fast as possible and go and attack the enemy's city. If that fails, it almost always loses. The manual gave it some hint in that direction.
vectorpushalmost 14 years ago
I am interested in the details regarding how the AI was able to map the manual to the game controls.
zalthoralmost 14 years ago
Taking RTFM to the next level. Yes.
评论 #2760978 未加载