Gamer, a General Game Playing Agent

被引：11

作者：

Kissmann, Peter ^{[1
]}

Edelkamp, Stefan ^{[1
]}

机构：

[1] Univ Bremen, Technol Zentrum Informat & Informationstech, Am Fallturm 1, D-28357 Bremen, Germany

来源：

KUNSTLICHE INTELLIGENZ | 2011年 / 25卷 / 01期

关键词：

General game playing; Instantiating games; Solving games; Symbolic search; UCT;

D O I：

10.1007/s13218-010-0078-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This work is concerned with our general game playing agent GAMER. In contrast to many other players, we do not only use a Prolog-like mechanism to infer knowledge about the current state and the available moves but instantiate the games to reduce the inference time in parallel UCT game tree search. Furthermore, we use the generated output to try to solve the games using symbolic search methods and thus play optimally.

引用

页码：49 / 52

页数：4

共 11 条

[1]

BRYANT RE, 1986, IEEE T COMPUT, V35, P677, DOI 10.1109/TC.1986.1676819

[2]

Cazenave T., 2007, P COMP GAM WORKSH, P93

[3]

CLUNE J, 2007, P 22 AAAI C ART INT, P1134

[4]

Edelkamp S., 2010, P MULT WIRTSCH GOTT, P2295

[5]

Finnsson H., 2008, AAAI, Vl, P259

[6]

Kissmann P., 2010, SOCS, P63

[7]

Kissmann P, 2010, LECT NOTES ARTIF INT, V6359, P255, DOI 10.1007/978-3-642-16111-7_29

[8] Bandit based Monte-Carlo planning [J].

Kocsis, Levente ;

Szepesvari, Csaba .

MACHINE LEARNING: ECML 2006, PROCEEDINGS, 2006, 4212 :282-293

[9]

LOVE N, 2006, GEN GAME PLAYING GAM

[10]

Mehat J, 2010, 13 BOARD GAM STUD C

← 1 2 →