TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Computer learns to play Civilization by reading the manual

95 点作者 thomas将近 14 年前

4 条评论

colanderman将近 14 年前
The source article is way more informative: <a href="http://web.mit.edu/newsoffice/2011/language-from-games-0712.html" rel="nofollow">http://web.mit.edu/newsoffice/2011/language-from-games-0712....</a>
评论 #2765265 未加载
评论 #2765267 未加载
roschdal将近 14 年前
According the the paper, they used Freeciv, because it is open source and they could modify the source code. Their source code is available here:<p><a href="http://groups.csail.mit.edu/rbg/code/civ/" rel="nofollow">http://groups.csail.mit.edu/rbg/code/civ/</a>
评论 #2766073 未加载
prosa将近 14 年前
Finally, someone learns to RTFM.
评论 #2765617 未加载
评论 #2765788 未加载
meric将近 14 年前
How do you know the manual affected how well the computer played? IMHO Put a machine learning algorithm into playing enough games and it isn't so unreasonable it would do better than the default AI on at least some games.<p>They need a control where the computer doesn't have access to a manual and compare to that.
评论 #2766325 未加载
评论 #2766693 未加载