The 2018 Hanabi competition

被引：0
作者：
Walton-Rivers, Joseph [1 ]
Williams, Piers R. [1 ]
Bartle, Richard [1 ]
机构：
[1] Univ Essex, Sch Comp Sci & Elect Engn, Colchester CO4 3SQ, Essex, England
来源：
2019 IEEE CONFERENCE ON GAMES (COG) | 2019年
基金：
英国工程与自然科学研究理事会;
关键词：
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：
This paper outlines the Hanabi competition, first run at CIG 2018, and returning for COG 2019. Hanabi presents a useful domain for game agents which must function in a cooperative environment. The paper presents the results of the two tracks which formed the 2018 competition and introduces the learning track, a new track for 2019 which allows the agents to collect statistics across multiple games.
引用
收藏
页数：8
相关论文
共 20 条
[1]   Hanabi is NP-hard, even for cheaters who look at their cards [J].
Baffler, Jean-Francois ;
Chiu, Man-Kwun ;
Diez, Yago ;
Korman, Matias ;
Mitsou, Valia ;
van Renssen, Andre ;
Roeloffzen, Marcel ;
Uno, Yushi .
THEORETICAL COMPUTER SCIENCE, 2017, 675 :43-55
[2]  
Bard N., 2019, arXiv
[3]  
Bauza A., 2010, HANABI BOARDGAME
[4]   Playing Hanabi Near-Optimally [J].
Bouzy, Bruno .
ADVANCES IN COMPUTER GAMES, ACG 2017, 2017, 10664 :51-62
[5]  
Canaan Rodrigo., 2018, 2018 IEEE Conference on Computational Intelligence and Games (CIG), P1
[6]   Information Set Monte Carlo Tree Search [J].
Cowling, Peter I. ;
Powley, Edward J. ;
Whitehouse, Daniel .
IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES, 2012, 4 (02) :120-143
[7]  
De Silva J., 2015, Mathematics Magazine, V88, P323, DOI DOI 10.4169/MATH.MAG.88.5.323
[8]  
Eger Markus, 2017, 2017 IEEE Conference on Computational Intelligence and Games (CIG), P68, DOI 10.1109/CIG.2017.8080417
[9]  
Foerster J. N., 2018, arXiv
[10]  
Gaina RD, 2016, COMPUT SCI ELECTR, P186, DOI 10.1109/CEEC.2016.7835911
12