View in EDS PDF Full Text

Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.

Saved in:
Bibliographic Details
Title: Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.
Authors: Everitt, Tom1,2, tomeveritt@google.com, Hutter, Marcus1,2, Kumar, Ramana1, Krakovna, Victoria1
Source: Synthese; Nov2021 Supplement 27, Vol. 198 Issue 27, p6435-6467, 33p
Database: Humanities Source
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: hus
DbLabel: Humanities Source
An: 153553308
AccessLevel: 2
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AU" term="%22Everitt%2C+Tom%22">Everitt, Tom</searchLink><relatesTo>1,2</relatesTo>, <i>tomeveritt@google.com</i><br /><searchLink fieldCode="AU" term="%22Hutter%2C+Marcus%22">Hutter, Marcus</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AU" term="%22Kumar%2C+Ramana%22">Kumar, Ramana</searchLink><relatesTo>1</relatesTo><br /><searchLink fieldCode="AU" term="%22Krakovna%2C+Victoria%22">Krakovna, Victoria</searchLink><relatesTo>1</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Synthese%22">Synthese</searchLink>; Nov2021 Supplement 27, Vol. 198 Issue 27, p6435-6467, 33p
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=hus&AN=153553308
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s11229-021-03141-4
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 33
        StartPage: 6435
    Titles:
      – TitleFull: Reward tampering problems and solutions in reinforcement learning: a causal influence diagram perspective.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Everitt, Tom
      – PersonEntity:
          Name:
            NameFull: Hutter, Marcus
      – PersonEntity:
          Name:
            NameFull: Kumar, Ramana
      – PersonEntity:
          Name:
            NameFull: Krakovna, Victoria
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 04
              M: 11
              Text: Nov2021 Supplement 27
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-print
              Value: 00397857
          Numbering:
            – Type: volume
              Value: 198
            – Type: issue
              Value: 27
          Titles:
            – TitleFull: Synthese
              Type: main
ResultId 1