On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study

Simo Linkola; Otto Hantula

doi:10.1007/978-3-319-77583-8_14

On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study

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

Abstract

We study how artistically creative agents may learn to select favorable collaboration partners. We consider a society of creative agents with varying skills and aesthetic preferences able to interact with each other by exchanging artifacts or through collaboration. The agents exhibit interaction awareness by modeling their peers and make decisions about collaboration based on the learned peer models. To test the peer models, we devise an experimental collaboration process for evolutionary art, where two agents create an artifact by evolving the same artifact set in turns. In an empirical evaluation, we focus on how effective peer models are in selecting collaboration partners and compare the results to a baseline where agents select collaboration partners randomly. We observe that peer models guide the agents to more beneficial collaborations.

Original language	English
Title of host publication	Computational Intelligence in Music, Sound, Art and Design : 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings
Editors	Antonios Liapis, Juan Jesús Romero Cardalda, Anikó Ekárt
Number of pages	17
Place of Publication	Cham
Publisher	Springer International Publishing AG
Publication date	4 Apr 2018
Pages	206-222
ISBN (Print)	978-3-319-77582-1
ISBN (Electronic)	978-3-319-77583-8
DOIs	https://doi.org/10.1007/978-3-319-77583-8_14
Publication status	Published - 4 Apr 2018
MoE publication type	A4 Article in conference proceedings
Event	International Conference on Computational Intelligence in Music, Sound, Art and Design - Parma, Italy Duration: 4 Apr 2018 → 6 Apr 2018 Conference number: 7

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer International Publishing AG
Volume	10783
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Fields of Science

113 Computer and information sciences
computational social creativity
evolutionary art
collaboration
learning from experience

Access to Document

10.1007/978-3-319-77583-8_14

linkola_hantula_-_EvoMUSART18Accepted author manuscript, 2.83 MB

CACS: Cooperation-Aware Software and Creative Self-Adaptivity
Toivonen, H. T., Hadaytullah, H., Linkola, S., Hantula, O. & Männistö, T.
SUOMEN AKATEMIA
01/01/2018 → 31/12/2019
Project: Research project

Cite this

Linkola, S., & Hantula, O. (2018). On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study. In A. Liapis, J. J. R. Cardalda, & A. Ekárt (Eds.), Computational Intelligence in Music, Sound, Art and Design: 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings (pp. 206-222). (Lecture Notes in Computer Science; Vol. 10783). Springer International Publishing AG. https://doi.org/10.1007/978-3-319-77583-8_14

Linkola, Simo ; Hantula, Otto. / On Collaborator Selection in Creative Agent Societies : An Evolutionary Art Case Study. Computational Intelligence in Music, Sound, Art and Design: 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings. editor / Antonios Liapis ; Juan Jesús Romero Cardalda ; Anikó Ekárt. Cham : Springer International Publishing AG, 2018. pp. 206-222 (Lecture Notes in Computer Science).

@inproceedings{f01d8015014d4cd29a5a098fdb2cb4ad,

title = "On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study",

abstract = "We study how artistically creative agents may learn to select favorable collaboration partners. We consider a society of creative agents with varying skills and aesthetic preferences able to interact with each other by exchanging artifacts or through collaboration. The agents exhibit interaction awareness by modeling their peers and make decisions about collaboration based on the learned peer models. To test the peer models, we devise an experimental collaboration process for evolutionary art, where two agents create an artifact by evolving the same artifact set in turns. In an empirical evaluation, we focus on how effective peer models are in selecting collaboration partners and compare the results to a baseline where agents select collaboration partners randomly. We observe that peer models guide the agents to more beneficial collaborations.",

keywords = "113 Computer and information sciences, computational social creativity, evolutionary art, collaboration, learning from experience",

author = "Simo Linkola and Otto Hantula",

year = "2018",

month = apr,

day = "4",

doi = "10.1007/978-3-319-77583-8_14",

language = "English",

isbn = "978-3-319-77582-1",

series = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing AG",

pages = "206--222",

editor = "Antonios Liapis and Cardalda, {Juan Jes{\'u}s Romero} and Anik{\'o} Ek{\'a}rt",

booktitle = "Computational Intelligence in Music, Sound, Art and Design",

address = "Switzerland",

note = "International Conference on Computational Intelligence in Music, Sound, Art and Design, EvoMUSART ; Conference date: 04-04-2018 Through 06-04-2018",

}

Linkola, S & Hantula, O 2018, On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study. in A Liapis, JJR Cardalda & A Ekárt (eds), Computational Intelligence in Music, Sound, Art and Design: 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings. Lecture Notes in Computer Science, vol. 10783, Springer International Publishing AG, Cham, pp. 206-222, International Conference on Computational Intelligence in Music, Sound, Art and Design, Parma, Italy, 04/04/2018. https://doi.org/10.1007/978-3-319-77583-8_14

On Collaborator Selection in Creative Agent Societies : An Evolutionary Art Case Study. / Linkola, Simo ; Hantula, Otto.

Computational Intelligence in Music, Sound, Art and Design: 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings. ed. / Antonios Liapis; Juan Jesús Romero Cardalda; Anikó Ekárt. Cham : Springer International Publishing AG, 2018. p. 206-222 (Lecture Notes in Computer Science; Vol. 10783).

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

TY - GEN

T1 - On Collaborator Selection in Creative Agent Societies

T2 - International Conference on Computational Intelligence in Music, Sound, Art and Design

AU - Linkola, Simo

AU - Hantula, Otto

N1 - Conference code: 7

PY - 2018/4/4

Y1 - 2018/4/4

N2 - We study how artistically creative agents may learn to select favorable collaboration partners. We consider a society of creative agents with varying skills and aesthetic preferences able to interact with each other by exchanging artifacts or through collaboration. The agents exhibit interaction awareness by modeling their peers and make decisions about collaboration based on the learned peer models. To test the peer models, we devise an experimental collaboration process for evolutionary art, where two agents create an artifact by evolving the same artifact set in turns. In an empirical evaluation, we focus on how effective peer models are in selecting collaboration partners and compare the results to a baseline where agents select collaboration partners randomly. We observe that peer models guide the agents to more beneficial collaborations.

AB - We study how artistically creative agents may learn to select favorable collaboration partners. We consider a society of creative agents with varying skills and aesthetic preferences able to interact with each other by exchanging artifacts or through collaboration. The agents exhibit interaction awareness by modeling their peers and make decisions about collaboration based on the learned peer models. To test the peer models, we devise an experimental collaboration process for evolutionary art, where two agents create an artifact by evolving the same artifact set in turns. In an empirical evaluation, we focus on how effective peer models are in selecting collaboration partners and compare the results to a baseline where agents select collaboration partners randomly. We observe that peer models guide the agents to more beneficial collaborations.

KW - 113 Computer and information sciences

KW - computational social creativity

KW - evolutionary art

KW - collaboration

KW - learning from experience

U2 - 10.1007/978-3-319-77583-8_14

DO - 10.1007/978-3-319-77583-8_14

M3 - Conference contribution

SN - 978-3-319-77582-1

T3 - Lecture Notes in Computer Science

SP - 206

EP - 222

BT - Computational Intelligence in Music, Sound, Art and Design

A2 - Liapis, Antonios

A2 - Cardalda, Juan Jesús Romero

A2 - Ekárt, Anikó

PB - Springer International Publishing AG

CY - Cham

Y2 - 4 April 2018 through 6 April 2018

ER -

Linkola S , Hantula O. On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study. In Liapis A, Cardalda JJR, Ekárt A, editors, Computational Intelligence in Music, Sound, Art and Design: 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings. Cham: Springer International Publishing AG. 2018. p. 206-222. (Lecture Notes in Computer Science). doi: 10.1007/978-3-319-77583-8_14

On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study

Abstract

Publication series

Fields of Science

Access to Document

Projects

CACS: Co­oper­a­tion-Aware Soft­ware and Cre­at­ive Self-Ad­aptiv­ity

Cite this

CACS: Cooperation-Aware Software and Creative Self-Adaptivity