View in EDS HTML Full Text PDF Full Text

Hierarchical reinforcement Thompson composition.

Saved in:
Bibliographic Details
Title: Hierarchical reinforcement Thompson composition.
Authors: Tanık, Güven Orkun1 (AUTHOR) orkun.tanik@metu.edu.tr, Ertekin, Şeyda1,2 (AUTHOR)
Source: Neural Computing & Applications. Jul2024, Vol. 36 Issue 20, p12317-12326. 10p.
Subjects: Artificial intelligence, Robust control, Intelligence officers, Decision trees, Problem solving
Abstract: Modern real-world control problems call for continuous control domains and robust, sample efficient and explainable control frameworks. We are presenting a framework for recursively composing control skills to solve compositional and progressively complex tasks. The framework promotes reuse of skills, and as a result quick adaptability to new tasks. The decision tree can be observed, providing insight into the agents' behavior. Furthermore, the skills can be transferred, modified or trained independently, which can simplify reward shaping and increase training speeds considerably. This paper is concerned with efficient composition of control algorithms using reinforcement learning and soft attention. Compositional and temporal abstraction is the key to improving learning and planning in reinforcement learning. Our Thompson sampling inspired soft-attention model is demonstrated to efficiently solve the composition problem. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computing & Applications is the property of Springer Nature 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.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 178316439
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Hierarchical reinforcement Thompson composition.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Tanık%2C+Güven+Orkun%22">Tanık, Güven Orkun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> orkun.tanik@metu.edu.tr</i><br /><searchLink fieldCode="AR" term="%22Ertekin%2C+Şeyda%22">Ertekin, Şeyda</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computing+%26+Applications%22">Neural Computing & Applications</searchLink>. Jul2024, Vol. 36 Issue 20, p12317-12326. 10p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Robust+control%22">Robust control</searchLink><br /><searchLink fieldCode="DE" term="%22Intelligence+officers%22">Intelligence officers</searchLink><br /><searchLink fieldCode="DE" term="%22Decision+trees%22">Decision trees</searchLink><br /><searchLink fieldCode="DE" term="%22Problem+solving%22">Problem solving</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Modern real-world control problems call for continuous control domains and robust, sample efficient and explainable control frameworks. We are presenting a framework for recursively composing control skills to solve compositional and progressively complex tasks. The framework promotes reuse of skills, and as a result quick adaptability to new tasks. The decision tree can be observed, providing insight into the agents' behavior. Furthermore, the skills can be transferred, modified or trained independently, which can simplify reward shaping and increase training speeds considerably. This paper is concerned with efficient composition of control algorithms using reinforcement learning and soft attention. Compositional and temporal abstraction is the key to improving learning and planning in reinforcement learning. Our Thompson sampling inspired soft-attention model is demonstrated to efficiently solve the composition problem. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neural Computing & Applications is the property of Springer Nature 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://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=178316439
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00521-024-09732-9
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 10
        StartPage: 12317
    Subjects:
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Robust control
        Type: general
      – SubjectFull: Intelligence officers
        Type: general
      – SubjectFull: Decision trees
        Type: general
      – SubjectFull: Problem solving
        Type: general
    Titles:
      – TitleFull: Hierarchical reinforcement Thompson composition.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Tanık, Güven Orkun
      – PersonEntity:
          Name:
            NameFull: Ertekin, Şeyda
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 11
              M: 07
              Text: Jul2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 09410643
          Numbering:
            – Type: volume
              Value: 36
            – Type: issue
              Value: 20
          Titles:
            – TitleFull: Neural Computing & Applications
              Type: main
ResultId 1