Evolutionary Procedural 2D Map Generation using Novelty Search

Johannes Karder; Andreas Scheibenpflug; Susanne Schaller; Stefan Wagner; Michael Affenzeller

doi:10.1145/2908961.2909047

Evolutionary Procedural 2D Map Generation using Novelty Search

Research Center Hagenberg

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

This paper presents an evolutionary approach to procedural content generation of 2D maps for computer games. To provide better adaptability to the map designer’s vision, user preference is incorporated to guide the algorithm. A cooperative method utilizes novelty search as a source of diverse solutions, which are then further optimized by multiple, subsequent genetic algorithms. We compare the results to a second approach based on multi-objective optimization, which takes the two conflicting goals of optimizing towards user preference and finding novel solutions as objective functions to build a Pareto front of maps.

Original language	English
Title of host publication	GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference
Editors	Tobias Friedrich
Publisher	ACM Sigevo
Pages	39-40
Number of pages	2
ISBN (Electronic)	9781450343237
ISBN (Print)	978-1-4503-4323-7
DOIs	https://doi.org/10.1145/2908961.2909047
Publication status	Published - 20 Jul 2016
Event	Genetic and Evolutionary Computation Conference (GECCO 2016) - Denver, Colorado, United States Duration: 20 Jul 2016 → 24 Jul 2016 http://gecco-2016.sigevo.org/

Publication series

Name	GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference

Conference

Conference	Genetic and Evolutionary Computation Conference (GECCO 2016)
Country/Territory	United States
City	Denver, Colorado
Period	20.07.2016 → 24.07.2016
Internet address	http://gecco-2016.sigevo.org/

Keywords

Procedural Content Generation
Search-based Procedural Content Generation
Novelty Search
Genetic Algorithm
HeuristicLab
Genetic algorithm
Heuristiclab
Novelty search
Search-based procedural content generation
Procedural content generation

Access to Document

10.1145/2908961.2909047

Cite this

Karder, J., Scheibenpflug, A., Schaller, S., Wagner, S., & Affenzeller, M. (2016). Evolutionary Procedural 2D Map Generation using Novelty Search. In T. Friedrich (Ed.), GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference (pp. 39-40). (GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference). ACM Sigevo. https://doi.org/10.1145/2908961.2909047

Karder, Johannes ; Scheibenpflug, Andreas ; Schaller, Susanne et al. / Evolutionary Procedural 2D Map Generation using Novelty Search. GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference. editor / Tobias Friedrich. ACM Sigevo, 2016. pp. 39-40 (GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference).

@inproceedings{9e2a01806a4449d8832d1841951bf10a,

title = "Evolutionary Procedural 2D Map Generation using Novelty Search",

abstract = "This paper presents an evolutionary approach to procedural content generation of 2D maps for computer games. To provide better adaptability to the map designer{\textquoteright}s vision, user preference is incorporated to guide the algorithm. A cooperative method utilizes novelty search as a source of diverse solutions, which are then further optimized by multiple, subsequent genetic algorithms. We compare the results to a second approach based on multi-objective optimization, which takes the two conflicting goals of optimizing towards user preference and finding novel solutions as objective functions to build a Pareto front of maps.",

keywords = "Procedural Content Generation, Search-based Procedural Content Generation, Novelty Search, Genetic Algorithm, HeuristicLab, Procedural Content Generation, Search-based Procedural Content Generation, Novelty Search, Genetic Algorithm, HeuristicLab, Genetic algorithm, Heuristiclab, Novelty search, Search-based procedural content generation, Procedural content generation",

author = "Johannes Karder and Andreas Scheibenpflug and Susanne Schaller and Stefan Wagner and Michael Affenzeller",

year = "2016",

month = jul,

day = "20",

doi = "10.1145/2908961.2909047",

language = "English",

isbn = "978-1-4503-4323-7",

series = "GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference",

publisher = "ACM Sigevo",

pages = "39--40",

editor = "Tobias Friedrich",

booktitle = "GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference",

note = "Genetic and Evolutionary Computation Conference (GECCO 2016) ; Conference date: 20-07-2016 Through 24-07-2016",

url = "http://gecco-2016.sigevo.org/",

}

Karder, J, Scheibenpflug, A, Schaller, S , Wagner, S & Affenzeller, M 2016, Evolutionary Procedural 2D Map Generation using Novelty Search. in T Friedrich (ed.), GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference. GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference, ACM Sigevo, pp. 39-40, Genetic and Evolutionary Computation Conference (GECCO 2016), Denver, Colorado, United States, 20.07.2016. https://doi.org/10.1145/2908961.2909047

Evolutionary Procedural 2D Map Generation using Novelty Search. / Karder, Johannes; Scheibenpflug, Andreas; Schaller, Susanne et al.
GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference. ed. / Tobias Friedrich. ACM Sigevo, 2016. p. 39-40 (GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference).

Research output: Chapter in Book/Report/Conference proceedings › Conference contribution › peer-review

TY - GEN

T1 - Evolutionary Procedural 2D Map Generation using Novelty Search

AU - Karder, Johannes

AU - Scheibenpflug, Andreas

AU - Schaller, Susanne

AU - Wagner, Stefan

AU - Affenzeller, Michael

PY - 2016/7/20

Y1 - 2016/7/20

N2 - This paper presents an evolutionary approach to procedural content generation of 2D maps for computer games. To provide better adaptability to the map designer’s vision, user preference is incorporated to guide the algorithm. A cooperative method utilizes novelty search as a source of diverse solutions, which are then further optimized by multiple, subsequent genetic algorithms. We compare the results to a second approach based on multi-objective optimization, which takes the two conflicting goals of optimizing towards user preference and finding novel solutions as objective functions to build a Pareto front of maps.

AB - This paper presents an evolutionary approach to procedural content generation of 2D maps for computer games. To provide better adaptability to the map designer’s vision, user preference is incorporated to guide the algorithm. A cooperative method utilizes novelty search as a source of diverse solutions, which are then further optimized by multiple, subsequent genetic algorithms. We compare the results to a second approach based on multi-objective optimization, which takes the two conflicting goals of optimizing towards user preference and finding novel solutions as objective functions to build a Pareto front of maps.

KW - Procedural Content Generation

KW - Search-based Procedural Content Generation

KW - Novelty Search

KW - Genetic Algorithm

KW - HeuristicLab

KW - Procedural Content Generation

KW - Search-based Procedural Content Generation

KW - Novelty Search

KW - Genetic Algorithm

KW - HeuristicLab

KW - Genetic algorithm

KW - Heuristiclab

KW - Novelty search

KW - Search-based procedural content generation

KW - Procedural content generation

UR - https://www.scopus.com/pages/publications/84986322638

U2 - 10.1145/2908961.2909047

DO - 10.1145/2908961.2909047

M3 - Conference contribution

SN - 978-1-4503-4323-7

T3 - GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference

SP - 39

EP - 40

BT - GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference

A2 - Friedrich, Tobias

PB - ACM Sigevo

T2 - Genetic and Evolutionary Computation Conference (GECCO 2016)

Y2 - 20 July 2016 through 24 July 2016

ER -

Karder J, Scheibenpflug A, Schaller S , Wagner S , Affenzeller M. Evolutionary Procedural 2D Map Generation using Novelty Search. In Friedrich T, editor, GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference. ACM Sigevo. 2016. p. 39-40. (GECCO 2016 Companion - Proceedings of the 2016 Genetic and Evolutionary Computation Conference). doi: 10.1145/2908961.2909047

Evolutionary Procedural 2D Map Generation using Novelty Search

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this