Web-Based Interface for Data Labeling in StarCraft

被引:0
作者
Baek, In-Chang [1 ]
Kim, Kyung-Joong [1 ]
机构
[1] Sejong Univ, Dept Comp Sci & Engn, Seoul, South Korea
来源
PROCEEDINGS OF THE 2018 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND GAMES (CIG'18) | 2018年
基金
新加坡国家研究基金会;
关键词
human test; StarCraft AI; visualizer; replays;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, StarCraft AI has been very actively researched, largely via analysis of human replay data. However, such data are difficult to evaluate visually because they represent information from a limited environment, that of the game client. To solve this problem, we created an environment in which game screens are displayed on the web, allowing game progression to be evaluated at a glance. This allows the performance of more diverse and efficient experiments than conventional human testing. We show that human players label macro decisions (e.g., main force operations) during supervised StarCraft learning using a web-based interface.
引用
收藏
页码:498 / 499
页数:2
相关论文
共 4 条
[1]   Performance Evaluation Gaps in a Real-Time Strategy Game Between Human and Artificial Intelligence Players [J].
Kim, Man-Je ;
Kim, Kyung-Joong ;
Kim, Seungjun ;
Dey, Anind K. .
IEEE ACCESS, 2018, 6 :13575-13586
[2]  
Lin Z., 2017, ABS170802139 CORR
[3]  
Oh IS, 2015, IEEE CONF COMPU INTE, P536, DOI 10.1109/CIG.2015.7317899
[4]  
Weber B. G., 2010, 2010 IEEE Information Theory Workshop (ITW 2010), P115, DOI 10.1109/ITW.2010.5593363