Zobrazit v EDS

Razvoj programskog agenta-igrača za računalnu igru primjenom podržanog učenja ; Development of a software agent-player for a computer game using reinforcement learning

Uloženo v:
Podrobná bibliografie
Název: Razvoj programskog agenta-igrača za računalnu igru primjenom podržanog učenja ; Development of a software agent-player for a computer game using reinforcement learning
Autoři: Tadić, Bartul
Přispěvatelé: Popović, Siniša
Informace o vydavateli: Sveučilište u Zagrebu. Fakultet elektrotehnike i računarstva.
University of Zagreb. Faculty of Electrical Engineering and Computing.
Rok vydání: 2023
Sbírka: Croatian Digital Theses Repository (National and University Library in Zagreb)
Témata: Podržano učenje, ML-Agents Toolkit, strojno učenje, PPO algoritam, duboke neuronske mreže, Unity, Reinforcement learning, machine learning, PPO algorithm, deep neural networks, TEHNIČKE ZNANOSTI. Računarstvo, TECHNICAL SCIENCES. Computing
Popis: Zadnjih godina razvoj u dubokom podržanom učenju uvelike je imao primjenu u računalnim igricama i simulatorima zbog mogućnosti generiranja velikog broja interaktivnih i vizualno bogatih simulacija. U ovom radu, razvijeno je 3D okruženje koristeći pogonski sustav za računalne igre Unity te je opisana uporaba ML-Agents Toolkita za treniranje inteligentnih agenata pomoću gotove PyTorch implementacije algoritma Proximal Policy Optimization (PPO). U radu su uspoređene performanse različitih konfiguracija te opisano uspješno treniranje. Podržanim učenjem, agent je naučio vještine kretanja i istraživanja okoline, izbjegavanje neprijatelja te skupljanja novčića. Također, u radu je pokrivena teorija iza strojnog učenja, podržanog učenja, dubokih neuronskih mreža, algoritma PPO te korištenje programskog alata ML-Agents. ; In the last few years, deep reinforcement learning has found extensive application in computer games and simulators due to ability to generate a large number of interactive and visually-rich simulations. In this paper, a 3D environment is developed using Unity game engine, and the use of the ML-Agents Toolkit for training intelligent agents with a PyTorch implementation of the Proximal Policy Optimization (PPO) algorithm is described. The paper compares the performance of different configurations and discusses successful training outcomes. Through reinforcement learning, the agent has learned skills such as movement, environment exploration, enemy avoidance, and coin collection. Additionally, the paper covers the theory behind machine learning, reinforcement learning, deep neural networks, the PPO algorithm, and the use of ML-Agents Toolkit.
Druh dokumentu: bachelor thesis
Popis souboru: application/pdf
Jazyk: Croatian
Relation: https://zir.nsk.hr/islandora/object/fer:11013; https://urn.nsk.hr/urn:nbn:hr:168:774527; https://repozitorij.unizg.hr/islandora/object/fer:11013; https://repozitorij.unizg.hr/islandora/object/fer:11013/datastream/PDF
Dostupnost: https://zir.nsk.hr/islandora/object/fer:11013
https://urn.nsk.hr/urn:nbn:hr:168:774527
https://repozitorij.unizg.hr/islandora/object/fer:11013
https://repozitorij.unizg.hr/islandora/object/fer:11013/datastream/PDF
Rights: http://rightsstatements.org/vocab/InC/1.0/ ; info:eu-repo/semantics/closedAccess
Přístupové číslo: edsbas.C0C4D7AA
Databáze: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://zir.nsk.hr/islandora/object/fer:11013#
    Name: EDS - BASE (s4221598)
    Category: fullText
    Text: View record from BASE
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Tadi%C4%87%20B
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsbas
DbLabel: BASE
An: edsbas.C0C4D7AA
RelevancyScore: 796
AccessLevel: 3
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 795.653564453125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Razvoj programskog agenta-igrača za računalnu igru primjenom podržanog učenja ; Development of a software agent-player for a computer game using reinforcement learning
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Tadić%2C+Bartul%22">Tadić, Bartul</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Popović, Siniša
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Sveučilište u Zagrebu. Fakultet elektrotehnike i računarstva.<br />University of Zagreb. Faculty of Electrical Engineering and Computing.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2023
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Croatian Digital Theses Repository (National and University Library in Zagreb)
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Podržano+učenje%22">Podržano učenje</searchLink><br /><searchLink fieldCode="DE" term="%22ML-Agents+Toolkit%22">ML-Agents Toolkit</searchLink><br /><searchLink fieldCode="DE" term="%22strojno+učenje%22">strojno učenje</searchLink><br /><searchLink fieldCode="DE" term="%22PPO+algoritam%22">PPO algoritam</searchLink><br /><searchLink fieldCode="DE" term="%22duboke+neuronske+mreže%22">duboke neuronske mreže</searchLink><br /><searchLink fieldCode="DE" term="%22Unity%22">Unity</searchLink><br /><searchLink fieldCode="DE" term="%22Reinforcement+learning%22">Reinforcement learning</searchLink><br /><searchLink fieldCode="DE" term="%22machine+learning%22">machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22PPO+algorithm%22">PPO algorithm</searchLink><br /><searchLink fieldCode="DE" term="%22deep+neural+networks%22">deep neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22TEHNIČKE+ZNANOSTI%2E+Računarstvo%22">TEHNIČKE ZNANOSTI. Računarstvo</searchLink><br /><searchLink fieldCode="DE" term="%22TECHNICAL+SCIENCES%2E+Computing%22">TECHNICAL SCIENCES. Computing</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Zadnjih godina razvoj u dubokom podržanom učenju uvelike je imao primjenu u računalnim igricama i simulatorima zbog mogućnosti generiranja velikog broja interaktivnih i vizualno bogatih simulacija. U ovom radu, razvijeno je 3D okruženje koristeći pogonski sustav za računalne igre Unity te je opisana uporaba ML-Agents Toolkita za treniranje inteligentnih agenata pomoću gotove PyTorch implementacije algoritma Proximal Policy Optimization (PPO). U radu su uspoređene performanse različitih konfiguracija te opisano uspješno treniranje. Podržanim učenjem, agent je naučio vještine kretanja i istraživanja okoline, izbjegavanje neprijatelja te skupljanja novčića. Također, u radu je pokrivena teorija iza strojnog učenja, podržanog učenja, dubokih neuronskih mreža, algoritma PPO te korištenje programskog alata ML-Agents. ; In the last few years, deep reinforcement learning has found extensive application in computer games and simulators due to ability to generate a large number of interactive and visually-rich simulations. In this paper, a 3D environment is developed using Unity game engine, and the use of the ML-Agents Toolkit for training intelligent agents with a PyTorch implementation of the Proximal Policy Optimization (PPO) algorithm is described. The paper compares the performance of different configurations and discusses successful training outcomes. Through reinforcement learning, the agent has learned skills such as movement, environment exploration, enemy avoidance, and coin collection. Additionally, the paper covers the theory behind machine learning, reinforcement learning, deep neural networks, the PPO algorithm, and the use of ML-Agents Toolkit.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: bachelor thesis
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: Croatian
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://zir.nsk.hr/islandora/object/fer:11013; https://urn.nsk.hr/urn:nbn:hr:168:774527; https://repozitorij.unizg.hr/islandora/object/fer:11013; https://repozitorij.unizg.hr/islandora/object/fer:11013/datastream/PDF
– Name: URL
  Label: Availability
  Group: URL
  Data: https://zir.nsk.hr/islandora/object/fer:11013<br />https://urn.nsk.hr/urn:nbn:hr:168:774527<br />https://repozitorij.unizg.hr/islandora/object/fer:11013<br />https://repozitorij.unizg.hr/islandora/object/fer:11013/datastream/PDF
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: http://rightsstatements.org/vocab/InC/1.0/ ; info:eu-repo/semantics/closedAccess
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.C0C4D7AA
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.C0C4D7AA
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: Croatian
    Subjects:
      – SubjectFull: Podržano učenje
        Type: general
      – SubjectFull: ML-Agents Toolkit
        Type: general
      – SubjectFull: strojno učenje
        Type: general
      – SubjectFull: PPO algoritam
        Type: general
      – SubjectFull: duboke neuronske mreže
        Type: general
      – SubjectFull: Unity
        Type: general
      – SubjectFull: Reinforcement learning
        Type: general
      – SubjectFull: machine learning
        Type: general
      – SubjectFull: PPO algorithm
        Type: general
      – SubjectFull: deep neural networks
        Type: general
      – SubjectFull: TEHNIČKE ZNANOSTI. Računarstvo
        Type: general
      – SubjectFull: TECHNICAL SCIENCES. Computing
        Type: general
    Titles:
      – TitleFull: Razvoj programskog agenta-igrača za računalnu igru primjenom podržanog učenja ; Development of a software agent-player for a computer game using reinforcement learning
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Tadić, Bartul
      – PersonEntity:
          Name:
            NameFull: Popović, Siniša
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2023
          Identifiers:
            – Type: issn-locals
              Value: edsbas
ResultId 1