Zobraziť v EDS

Curiosity-Driven Exploration in Reinforcement Learning: An Adaptive Self-Supervised Learning Approach for Playing Action Games.

Uložené v:
Podrobná bibliografia
Názov: Curiosity-Driven Exploration in Reinforcement Learning: An Adaptive Self-Supervised Learning Approach for Playing Action Games.
Autori: Farooq, Sehar Shahzad, Rahman, Hameedur, Abdul Wahid, Samiya, Alyan Ansari, Muhammad, Abdul Wahid, Saira, Lee, Hosu
Zdroj: Computers (2073-431X); Oct2025, Vol. 14 Issue 10, p434, 25p
Predmety: REINFORCEMENT learning, INTRINSIC motivation, ACTION & adventure films, MACHINE learning, PLAY environments, LEARNING by discovery
Abstrakt: Games are considered a suitable and standard benchmark for checking the performance of artificial intelligence-based algorithms in terms of training, evaluating, and comparing the performance of AI agents. In this research, an application of the Intrinsic Curiosity Module (ICM) and the Asynchronous Advantage Actor–Critic (A3C) algorithm is explored using action games. Having been proven successful in several gaming environments, its effectiveness in action games is rarely explored. Providing efficient learning and adaptation facilities, this research aims to assess whether integrating ICM with A3C promotes curiosity-driven explorations and adaptive learning in action games. Using the MAME Toolkit library, we interface with the game environments, preprocess game screens to focus on relevant visual elements, and create diverse game episodes for training. The A3C policy is optimized using the Proximal Policy Optimization (PPO) algorithm with tuned hyperparameters. Comparisons are made with baseline methods, including vanilla A3C, ICM with pixel-based predictions, and state-of-the-art exploration techniques. Additionally, we evaluate the agent's generalization capability in separate environments. The results demonstrate that ICM and A3C effectively promote curiosity-driven exploration in action games, with the agent learning exploration behaviors without relying solely on external rewards. Notably, we also observed an improved efficiency and learning speed compared to baseline approaches. This research contributes to curiosity-driven exploration in reinforcement learning-based virtual environments and provides insights into the exploration of complex action games. Successfully applying ICM and A3C in action games presents exciting opportunities for adaptive learning and efficient exploration in challenging real-world environments. [ABSTRACT FROM AUTHOR]
Copyright of Computers (2073-431X) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáza: Complementary Index
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edb&genre=article&issn=2073431X&ISBN=&volume=14&issue=10&date=20251001&spage=434&pages=434-458&title=Computers (2073-431X)&atitle=Curiosity-Driven%20Exploration%20in%20Reinforcement%20Learning%3A%20An%20Adaptive%20Self-Supervised%20Learning%20Approach%20for%20Playing%20Action%20Games.&aulast=Farooq%2C%20Sehar%20Shahzad&id=DOI:10.3390/computers14100434
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Farooq%20SS
    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: edb
DbLabel: Complementary Index
An: 188998601
RelevancyScore: 1082
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1082.1455078125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Curiosity-Driven Exploration in Reinforcement Learning: An Adaptive Self-Supervised Learning Approach for Playing Action Games.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Farooq%2C+Sehar+Shahzad%22">Farooq, Sehar Shahzad</searchLink><br /><searchLink fieldCode="AR" term="%22Rahman%2C+Hameedur%22">Rahman, Hameedur</searchLink><br /><searchLink fieldCode="AR" term="%22Abdul+Wahid%2C+Samiya%22">Abdul Wahid, Samiya</searchLink><br /><searchLink fieldCode="AR" term="%22Alyan+Ansari%2C+Muhammad%22">Alyan Ansari, Muhammad</searchLink><br /><searchLink fieldCode="AR" term="%22Abdul+Wahid%2C+Saira%22">Abdul Wahid, Saira</searchLink><br /><searchLink fieldCode="AR" term="%22Lee%2C+Hosu%22">Lee, Hosu</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: Computers (2073-431X); Oct2025, Vol. 14 Issue 10, p434, 25p
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22REINFORCEMENT+learning%22">REINFORCEMENT learning</searchLink><br /><searchLink fieldCode="DE" term="%22INTRINSIC+motivation%22">INTRINSIC motivation</searchLink><br /><searchLink fieldCode="DE" term="%22ACTION+%26+adventure+films%22">ACTION & adventure films</searchLink><br /><searchLink fieldCode="DE" term="%22MACHINE+learning%22">MACHINE learning</searchLink><br /><searchLink fieldCode="DE" term="%22PLAY+environments%22">PLAY environments</searchLink><br /><searchLink fieldCode="DE" term="%22LEARNING+by+discovery%22">LEARNING by discovery</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Games are considered a suitable and standard benchmark for checking the performance of artificial intelligence-based algorithms in terms of training, evaluating, and comparing the performance of AI agents. In this research, an application of the Intrinsic Curiosity Module (ICM) and the Asynchronous Advantage Actor–Critic (A3C) algorithm is explored using action games. Having been proven successful in several gaming environments, its effectiveness in action games is rarely explored. Providing efficient learning and adaptation facilities, this research aims to assess whether integrating ICM with A3C promotes curiosity-driven explorations and adaptive learning in action games. Using the MAME Toolkit library, we interface with the game environments, preprocess game screens to focus on relevant visual elements, and create diverse game episodes for training. The A3C policy is optimized using the Proximal Policy Optimization (PPO) algorithm with tuned hyperparameters. Comparisons are made with baseline methods, including vanilla A3C, ICM with pixel-based predictions, and state-of-the-art exploration techniques. Additionally, we evaluate the agent's generalization capability in separate environments. The results demonstrate that ICM and A3C effectively promote curiosity-driven exploration in action games, with the agent learning exploration behaviors without relying solely on external rewards. Notably, we also observed an improved efficiency and learning speed compared to baseline approaches. This research contributes to curiosity-driven exploration in reinforcement learning-based virtual environments and provides insights into the exploration of complex action games. Successfully applying ICM and A3C in action games presents exciting opportunities for adaptive learning and efficient exploration in challenging real-world environments. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label:
  Group: Ab
  Data: <i>Copyright of Computers (2073-431X) is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edb&AN=188998601
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/computers14100434
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 25
        StartPage: 434
    Subjects:
      – SubjectFull: REINFORCEMENT learning
        Type: general
      – SubjectFull: INTRINSIC motivation
        Type: general
      – SubjectFull: ACTION & adventure films
        Type: general
      – SubjectFull: MACHINE learning
        Type: general
      – SubjectFull: PLAY environments
        Type: general
      – SubjectFull: LEARNING by discovery
        Type: general
    Titles:
      – TitleFull: Curiosity-Driven Exploration in Reinforcement Learning: An Adaptive Self-Supervised Learning Approach for Playing Action Games.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Farooq, Sehar Shahzad
      – PersonEntity:
          Name:
            NameFull: Rahman, Hameedur
      – PersonEntity:
          Name:
            NameFull: Abdul Wahid, Samiya
      – PersonEntity:
          Name:
            NameFull: Alyan Ansari, Muhammad
      – PersonEntity:
          Name:
            NameFull: Abdul Wahid, Saira
      – PersonEntity:
          Name:
            NameFull: Lee, Hosu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 10
              Text: Oct2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 2073431X
          Numbering:
            – Type: volume
              Value: 14
            – Type: issue
              Value: 10
          Titles:
            – TitleFull: Computers (2073-431X)
              Type: main
ResultId 1