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

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

Abstrakti

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.

Alkuperäiskieli	englanti
Otsikko	Computational Intelligence in Music, Sound, Art and Design : 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings
Toimittajat	Antonios Liapis, Juan Jesús Romero Cardalda, Anikó Ekárt
Sivumäärä	17
Julkaisupaikka	Cham
Kustantaja	Springer International Publishing AG
Julkaisupäivä	4 huhtikuuta 2018
Sivut	206-222
ISBN (painettu)	978-3-319-77582-1
ISBN (elektroninen)	978-3-319-77583-8
DOI - pysyväislinkit	https://doi.org/10.1007/978-3-319-77583-8_14
Tila	Julkaistu - 4 huhtikuuta 2018
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	International Conference on Computational Intelligence in Music, Sound, Art and Design - Parma, Italia Kesto: 4 huhtikuuta 2018 → 6 huhtikuuta 2018 Konferenssinumero: 7

Julkaisusarja

Nimi	Lecture Notes in Computer Science
Kustantaja	Springer International Publishing AG
Vuosikerta	10783
ISSN (painettu)	0302-9743
ISSN (elektroninen)	1611-3349

Tieteenalat

113 Tietojenkäsittely- ja informaatiotieteet

Pääsy asiakirjaan

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

linkola_hantula_-_EvoMUSART18Hyväksytty kirjoittajan käsikirjoitus, 2,83 MB

1 Päättynyt

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

Siteeraa tätä

Linkola, S., & Hantula, O. (2018). On Collaborator Selection in Creative Agent Societies: An Evolutionary Art Case Study. teoksessa A. Liapis, J. J. R. Cardalda, & A. Ekárt (Toimittajat), Computational Intelligence in Music, Sound, Art and Design: 7th International Conference, EvoMUSART 2018, Parma, Italy, April 4-6, 2018, Proceedings (Sivut 206-222). (Lecture Notes in Computer Science; Vuosikerta 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. Toimittaja / Antonios Liapis ; Juan Jesús Romero Cardalda ; Anikó Ekárt. Cham : Springer International Publishing AG, 2018. Sivut 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. julkaisussa A Liapis, JJR Cardalda & A Ekárt (toim), 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, Vuosikerta 10783, Springer International Publishing AG, Cham, Sivut 206-222, International Conference on Computational Intelligence in Music, Sound, Art and Design, Parma, Italia, 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. toim. / Antonios Liapis; Juan Jesús Romero Cardalda; Anikó Ekárt. Cham : Springer International Publishing AG, 2018. s. 206-222 (Lecture Notes in Computer Science; Vuosikerta 10783).

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussa › Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

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. julkaisussa Liapis A, Cardalda JJR, Ekárt A, toimittajat, 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. s. 206-222. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-77583-8_14

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

Abstrakti

Julkaisusarja

Tieteenalat

Pääsy asiakirjaan

CACS: Co­oper­a­tion-Aware Soft­ware and Cre­at­ive Self-Ad­aptiv­ity

Siteeraa tätä

CACS: Cooperation-Aware Software and Creative Self-Adaptivity