Optimizing Visual Properties of Game Content through Neuroevolution

Antonios Liapis; Georgios N. Yannakakis; Julian Togelius

Optimizing Visual Properties of Game Content through Neuroevolution

Antonios Liapis, Georgios N. Yannakakis, Julian Togelius

Research output: Contribution to conference - NOT published in proceeding or journal › Poster › Research › peer-review

Abstract

This paper presents a search-based approach to generating
game content that satisfies both gameplay requirements
and user-expressed aesthetic criteria. Using evolutionary
constraint satisfaction, we search for spaceships (for a
space combat game) represented as compositional pattern-producing
networks. While the gameplay requirements are
satisfied by ad-hoc defined constraints, the aesthetic evaluation
function can also be informed by human aesthetic judgement.
This is achieved using indirect interactive evolution,
where an evaluation function re-weights an array of aesthetic
criteria based on the choices of a human player. Early results
show that we can create aesthetically diverse and interesting
spaceships while retaining in-game functionality.

Original language	English
Publication date	2011
Number of pages	6
Publication status	Published - 2011
Event	Seventh Artificial Intelligence and Interactive Digital Entertainment Conference - Palo Alto, United States Duration: 12 Oct 2011 → 14 Oct 2011 Conference number: 7th http://www.aiide.org/aiide11/

Conference

Conference	Seventh Artificial Intelligence and Interactive Digital Entertainment Conference
Number	7th
Country/Territory	United States
City	Palo Alto
Period	12/10/2011 → 14/10/2011
Internet address	http://www.aiide.org/aiide11/

Access to Document

http://www.aaai.org/ocs/index.php/AIIDE/AIIDE11/paper/viewPaper/4053

Cite this

@conference{5f3753c5fb0b4795b41af0c375f15ba8,

title = "Optimizing Visual Properties of Game Content through Neuroevolution",

abstract = "This paper presents a search-based approach to generatinggame content that satisfies both gameplay requirementsand user-expressed aesthetic criteria. Using evolutionaryconstraint satisfaction, we search for spaceships (for aspace combat game) represented as compositional pattern-producingnetworks. While the gameplay requirements aresatisfied by ad-hoc defined constraints, the aesthetic evaluationfunction can also be informed by human aesthetic judgement.This is achieved using indirect interactive evolution,where an evaluation function re-weights an array of aestheticcriteria based on the choices of a human player. Early resultsshow that we can create aesthetically diverse and interestingspaceships while retaining in-game functionality.",

author = "Antonios Liapis and Yannakakis, {Georgios N.} and Julian Togelius",

year = "2011",

language = "English",

note = "Seventh Artificial Intelligence and Interactive Digital Entertainment Conference, AIIDE-11 ; Conference date: 12-10-2011 Through 14-10-2011",

url = "http://www.aiide.org/aiide11/",

}

Optimizing Visual Properties of Game Content through Neuroevolution. / Liapis, Antonios; Yannakakis, Georgios N.; Togelius, Julian.
2011. Poster session presented at Seventh Artificial Intelligence and Interactive Digital Entertainment Conference, Palo Alto, United States.

Research output: Contribution to conference - NOT published in proceeding or journal › Poster › Research › peer-review

TY - CONF

T1 - Optimizing Visual Properties of Game Content through Neuroevolution

AU - Liapis, Antonios

AU - Yannakakis, Georgios N.

AU - Togelius, Julian

N1 - Conference code: 7th

PY - 2011

Y1 - 2011

N2 - This paper presents a search-based approach to generatinggame content that satisfies both gameplay requirementsand user-expressed aesthetic criteria. Using evolutionaryconstraint satisfaction, we search for spaceships (for aspace combat game) represented as compositional pattern-producingnetworks. While the gameplay requirements aresatisfied by ad-hoc defined constraints, the aesthetic evaluationfunction can also be informed by human aesthetic judgement.This is achieved using indirect interactive evolution,where an evaluation function re-weights an array of aestheticcriteria based on the choices of a human player. Early resultsshow that we can create aesthetically diverse and interestingspaceships while retaining in-game functionality.

AB - This paper presents a search-based approach to generatinggame content that satisfies both gameplay requirementsand user-expressed aesthetic criteria. Using evolutionaryconstraint satisfaction, we search for spaceships (for aspace combat game) represented as compositional pattern-producingnetworks. While the gameplay requirements aresatisfied by ad-hoc defined constraints, the aesthetic evaluationfunction can also be informed by human aesthetic judgement.This is achieved using indirect interactive evolution,where an evaluation function re-weights an array of aestheticcriteria based on the choices of a human player. Early resultsshow that we can create aesthetically diverse and interestingspaceships while retaining in-game functionality.

M3 - Poster

T2 - Seventh Artificial Intelligence and Interactive Digital Entertainment Conference

Y2 - 12 October 2011 through 14 October 2011

ER -

Optimizing Visual Properties of Game Content through Neuroevolution

Abstract

Conference

Access to Document

Fingerprint

Cite this