Modelling and evaluation of complex scenarios with the Strategy Game Description Language

Tobias Mahlmann; Julian Togelius; Georgios N. Yannakakis

doi:10.1109/CIG.2011.6032004

Modelling and evaluation of complex scenarios with the Strategy Game Description Language

Tobias Mahlmann, Julian Togelius, Georgios N. Yannakakis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The Strategy Game Description Game Language (SGDL) is intended to become a complete description of all aspects of strategy games, including rules, parameters, scenarios, maps, and unit types. Our aim is to be able to model a wide variety of strategy games, simple ones as well as complex commercially available titles. In our previous work [1] we introduced the basic concepts of modelling game rules in a tree structure and evaluating them through simulated playthrough. In this paper we present some additions to the language and discuss and compare three methods to evaluate the quality of a set of game rules in two different scenarios. We find that the proposed evaluation measures are complementary, and depend on the artificial agent used.

Original language	English (US)
Title of host publication	2011 IEEE Conference on Computational Intelligence and Games, CIG 2011
Pages	174-181
Number of pages	8
DOIs	https://doi.org/10.1109/CIG.2011.6032004
State	Published - 2011
Event	2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011 - Seoul, Korea, Republic of Duration: Aug 31 2011 → Sep 3 2011

Publication series

Name	2011 IEEE Conference on Computational Intelligence and Games, CIG 2011

Other

Other	2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011
Country/Territory	Korea, Republic of
City	Seoul
Period	8/31/11 → 9/3/11

ASJC Scopus subject areas

Artificial Intelligence
Computer Vision and Pattern Recognition
Human-Computer Interaction
Software

Access to Document

10.1109/CIG.2011.6032004

Cite this

Modelling and evaluation of complex scenarios with the Strategy Game Description Language. / Mahlmann, Tobias; Togelius, Julian; Yannakakis, Georgios N.
2011 IEEE Conference on Computational Intelligence and Games, CIG 2011. 2011. p. 174-181 6032004 (2011 IEEE Conference on Computational Intelligence and Games, CIG 2011).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mahlmann, T, Togelius, J & Yannakakis, GN 2011, Modelling and evaluation of complex scenarios with the Strategy Game Description Language. in 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011., 6032004, 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011, pp. 174-181, 2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011, Seoul, Korea, Republic of, 8/31/11. https://doi.org/10.1109/CIG.2011.6032004

@inproceedings{10047fe5696c41159ff102e6440ea267,

title = "Modelling and evaluation of complex scenarios with the Strategy Game Description Language",

abstract = "The Strategy Game Description Game Language (SGDL) is intended to become a complete description of all aspects of strategy games, including rules, parameters, scenarios, maps, and unit types. Our aim is to be able to model a wide variety of strategy games, simple ones as well as complex commercially available titles. In our previous work [1] we introduced the basic concepts of modelling game rules in a tree structure and evaluating them through simulated playthrough. In this paper we present some additions to the language and discuss and compare three methods to evaluate the quality of a set of game rules in two different scenarios. We find that the proposed evaluation measures are complementary, and depend on the artificial agent used.",

author = "Tobias Mahlmann and Julian Togelius and Yannakakis, {Georgios N.}",

year = "2011",

doi = "10.1109/CIG.2011.6032004",

language = "English (US)",

isbn = "9781457700095",

series = "2011 IEEE Conference on Computational Intelligence and Games, CIG 2011",

pages = "174--181",

booktitle = "2011 IEEE Conference on Computational Intelligence and Games, CIG 2011",

note = "2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011 ; Conference date: 31-08-2011 Through 03-09-2011",

}

TY - GEN

T1 - Modelling and evaluation of complex scenarios with the Strategy Game Description Language

AU - Mahlmann, Tobias

AU - Togelius, Julian

AU - Yannakakis, Georgios N.

PY - 2011

Y1 - 2011

N2 - The Strategy Game Description Game Language (SGDL) is intended to become a complete description of all aspects of strategy games, including rules, parameters, scenarios, maps, and unit types. Our aim is to be able to model a wide variety of strategy games, simple ones as well as complex commercially available titles. In our previous work [1] we introduced the basic concepts of modelling game rules in a tree structure and evaluating them through simulated playthrough. In this paper we present some additions to the language and discuss and compare three methods to evaluate the quality of a set of game rules in two different scenarios. We find that the proposed evaluation measures are complementary, and depend on the artificial agent used.

AB - The Strategy Game Description Game Language (SGDL) is intended to become a complete description of all aspects of strategy games, including rules, parameters, scenarios, maps, and unit types. Our aim is to be able to model a wide variety of strategy games, simple ones as well as complex commercially available titles. In our previous work [1] we introduced the basic concepts of modelling game rules in a tree structure and evaluating them through simulated playthrough. In this paper we present some additions to the language and discuss and compare three methods to evaluate the quality of a set of game rules in two different scenarios. We find that the proposed evaluation measures are complementary, and depend on the artificial agent used.

UR - http://www.scopus.com/inward/record.url?scp=80054037273&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80054037273&partnerID=8YFLogxK

U2 - 10.1109/CIG.2011.6032004

DO - 10.1109/CIG.2011.6032004

M3 - Conference contribution

AN - SCOPUS:80054037273

SN - 9781457700095

T3 - 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011

SP - 174

EP - 181

BT - 2011 IEEE Conference on Computational Intelligence and Games, CIG 2011

T2 - 2011 7th IEEE International Conference on Computational Intelligence and Games, CIG 2011

Y2 - 31 August 2011 through 3 September 2011

ER -

Modelling and evaluation of complex scenarios with the Strategy Game Description Language

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this