没有合适的资源?快使用搜索试试~ 我知道了~
首页Artificial Intelligence and Games
Artificial Intelligence and Games
需积分: 10 181 浏览量
更新于2023-03-16
评论
收藏 4.83MB PDF 举报
Artificial Intelligence Games draft This is the first textbook dedicated to explaining how artificial intelligence (AI) techniques can be used in and for games.
资源详情
资源评论
资源推荐

DRAFT
Georgios N. Yannakakis and Julian Togelius
Artificial Intelligence and Games
October 6, 2017
Springer

DRAFT

DRAFT
To our families

DRAFT

DRAFT
Foreword
It is my great pleasure to write the foreword for this excellent and timely book.
Games have long been seen as the perfect test-bed for artificial intelligence (AI)
methods, and are also becoming an increasingly important application area. Game
AI is a broad field, covering everything from the challenge of making super-human
AI for difficult games such as Go or StarCraft, to creative applications such as the
automated generation of novel games.
Game AI is as old as AI itself, but over the last decade the field has seen mas-
sive expansion and enrichment with the inclusion of video games, which now com-
prise more than 50% of all published work in the area and enable us to address a
broader range of challenges that have great commercial, social, economic and scien-
tific interest. A great surge in research output occurred in 2005, coinciding with both
the first IEEE Symposium (Conference) on Computational Intelligence and Games
(CIG)—which I co-chaired with Graham Kendall—and the first AAAI AIIDE Con-
ference (Artificial Intelligence in Digital Entertainment). Since then this rich area of
research has been more explored and better understood. The Game AI community
pioneered much of the research which is now becoming (or about to become) more
mainstream AI, such as Monte Carlo Tree Search, procedural content generation,
playing games based on screen capture, and automated game design.
Over the last decade, progress in deep learning has had a profound and transfor-
mational effect on many difficult problems, including speech recognition, machine
translation, natural language understanding and computer vision. As a result, com-
puters can now achieve human-competitive performance in a wide range of percep-
tion and recognition tasks. Many of these systems are now available to the program-
mer via a range of so-called cognitive services. More recently, deep reinforcement
learning has achieved ground-breaking success in a number of difficult challenges,
including Go and the amazing feat of learning to play games directly from screen
capture (playing from pixels). It is fascinating to contemplate what this could mean
for games as we stumble towards human-level intelligence in an increasing number
of areas. The impacts will be significant for the intelligence of in-game characters,
the way in which we interact with them and for the way games are designed and
tested.
vii
剩余358页未读,继续阅读

















安全验证
文档复制为VIP权益,开通VIP直接复制

评论0