Academic Journal

Contrastive learning of generalized game representations

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Contrastive learning of generalized game representations
Συγγραφείς: Trivedi, Chintan, Liapis, Antonios, Yannakakis, Georgios N.
Στοιχεία εκδότη: arXiv
Έτος έκδοσης: 2021
Συλλογή: University of Malta: OAR@UM / L-Università ta' Malta
Θεματικοί όροι: Games -- Design, Computer games -- Programming, Video games -- Design, Motion -- Computer simulation, Interactive multimedia
Περιγραφή: Representing games through their pixels offers a promising approach for building general-purpose and versatile game models. While games are not merely images, neural network models trained on game pixels often capture differences of the visual style of the image rather than the content of the game. As a result, such models cannot generalize well even within similar games of the same genre. In this paper we build on recent advances in contrastive learning and showcase its benefits for representation learning in games. Learning to contrast images of games not only classifies games in a more efficient manner; it also yields models that separate games in a more meaningful fashion by ignoring the visual style and focusing, instead, on their content. Our results in a large dataset of sports video games containing 100k images across 175 games and 10 game genres suggest that contrastive learning is better suited for learning generalized game representations compared to conventional supervised learning. The findings of this study bring us closer to universal visual encoders for games that can be reused across previously unseen games without requiring retraining or fine-tuning. ; N/A
Τύπος εγγράφου: article in journal/newspaper
Γλώσσα: English
Relation: Trivedi, C., Liapis, A., & Yannakakis, G. N. (2021). Contrastive learning of generalized game representations. arXiv preprint arXiv:2106.10060.; https://www.um.edu.mt/library/oar/handle/123456789/80762
Διαθεσιμότητα: https://www.um.edu.mt/library/oar/handle/123456789/80762
Rights: info:eu-repo/semantics/openAccess ; The copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder.
Αριθμός Καταχώρησης: edsbas.1F9850AB
Βάση Δεδομένων: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://www.um.edu.mt/library/oar/handle/123456789/80762#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.1F9850AB
RelevancyScore: 906
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 906.347900390625
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Contrastive learning of generalized game representations
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Trivedi%2C+Chintan%22">Trivedi, Chintan</searchLink><br /><searchLink fieldCode="AR" term="%22Liapis%2C+Antonios%22">Liapis, Antonios</searchLink><br /><searchLink fieldCode="AR" term="%22Yannakakis%2C+Georgios+N%2E%22">Yannakakis, Georgios N.</searchLink>
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: arXiv
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2021
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: University of Malta: OAR@UM / L-Università ta' Malta
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Games+--+Design%22">Games -- Design</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+games+--+Programming%22">Computer games -- Programming</searchLink><br /><searchLink fieldCode="DE" term="%22Video+games+--+Design%22">Video games -- Design</searchLink><br /><searchLink fieldCode="DE" term="%22Motion+--+Computer+simulation%22">Motion -- Computer simulation</searchLink><br /><searchLink fieldCode="DE" term="%22Interactive+multimedia%22">Interactive multimedia</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Representing games through their pixels offers a promising approach for building general-purpose and versatile game models. While games are not merely images, neural network models trained on game pixels often capture differences of the visual style of the image rather than the content of the game. As a result, such models cannot generalize well even within similar games of the same genre. In this paper we build on recent advances in contrastive learning and showcase its benefits for representation learning in games. Learning to contrast images of games not only classifies games in a more efficient manner; it also yields models that separate games in a more meaningful fashion by ignoring the visual style and focusing, instead, on their content. Our results in a large dataset of sports video games containing 100k images across 175 games and 10 game genres suggest that contrastive learning is better suited for learning generalized game representations compared to conventional supervised learning. The findings of this study bring us closer to universal visual encoders for games that can be reused across previously unseen games without requiring retraining or fine-tuning. ; N/A
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article in journal/newspaper
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: Trivedi, C., Liapis, A., & Yannakakis, G. N. (2021). Contrastive learning of generalized game representations. arXiv preprint arXiv:2106.10060.; https://www.um.edu.mt/library/oar/handle/123456789/80762
– Name: URL
  Label: Availability
  Group: URL
  Data: https://www.um.edu.mt/library/oar/handle/123456789/80762
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: info:eu-repo/semantics/openAccess ; The copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder.
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.1F9850AB
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.1F9850AB
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Games -- Design
        Type: general
      – SubjectFull: Computer games -- Programming
        Type: general
      – SubjectFull: Video games -- Design
        Type: general
      – SubjectFull: Motion -- Computer simulation
        Type: general
      – SubjectFull: Interactive multimedia
        Type: general
    Titles:
      – TitleFull: Contrastive learning of generalized game representations
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Trivedi, Chintan
      – PersonEntity:
          Name:
            NameFull: Liapis, Antonios
      – PersonEntity:
          Name:
            NameFull: Yannakakis, Georgios N.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1