DocumentCode :
62083
Title :
Passing a Hide-and-Seek Third-Person Turing Test
Author :
Cenkner, Andrew ; Bulitko, Vadim ; Spetch, Marcia ; Legge, Eric ; Anderson, Craig G. ; Brown, Michael
Author_Institution :
Dept. of Comput. Sci., Univ. of Alberta, Edmonton, AB, Canada
Volume :
6
Issue :
1
fYear :
2014
fDate :
Mar-14
Firstpage :
18
Lastpage :
30
Abstract :
Hiding and seeking are cognitive abilities frequently demonstrated by humans in both real life and video games. To determine to which extent these abilities can be replicated with AI, we introduce a specialized version of the Turing test for hiding and seeking. We then develop a computer agent that passes the test by appearing indistinguishable from human behavior to a panel of human judges. We analyze the AI techniques that enable the agent to imitate human hide-and-seek behavior and their relative contribution to the agent´s performance.
Keywords :
computer games; multi-agent systems; AI techniques; cognitive abilities; computer agent; hide-and-seek third-person Turing test; human behavior; video games; Artificial intelligence; Computers; Games; Hidden Markov models; Indexes; Training; Training data; AI bots; Turing test; hide-and-seek behavior;
fLanguage :
English
Journal_Title :
Computational Intelligence and AI in Games, IEEE Transactions on
Publisher :
ieee
ISSN :
1943-068X
Type :
jour
DOI :
10.1109/TCIAIG.2013.2275162
Filename :
6571220
Link To Document :
بازگشت