Conference
View in EDS

Policy graphs and intention: answering 'why' and 'how' from a telic perspective

Bibliographic Details
Title: Policy graphs and intention: answering 'why' and 'how' from a telic perspective
Authors: Giménez Ábalos, Víctor, Álvarez Napagao, Sergio, Tormos Llorente, Adrián, Cortés García, Claudio Ulises, Vázquez Salceda, Javier
Source: UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)
Publisher Information: International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025.
Publication Year: 2025
Subject Terms: Explainable agency, Telic explanations, XAI, Post-hoc explainability, Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Agents intel·ligents, Interpretability, Intentions, Reliability, Agent explainability
Description: Agents are a special kind of AI-based software in that they interact in complex environments and have increased potential for emergent behaviour. Explaining such behaviour is key to deploying trustworthy AI, but the increasing complexity and opaque nature of many agent implementations makes this hard. In this work, we reuse the Policy Graphs method --which can be used to explain opaque agent behaviour-- and enhance it to query it with hypotheses of desirable situations. These hypotheses are used to compute a numerical value to examine agent intentions at any particular moment, as a function of how likely the agent is to bring about a hypothesised desirable situation. We emphasise the relevance of how this approach has full epistemic traceability, and each belief used by the algorithms providing answers is backed by specific facts from its construction process. We show the numeric approach provides a robust and intuitive way to provide telic explainability (explaining current actions from the perspective of bringing about situations), and allows to evaluate the interpretability of behaviour of the agent based on the explanations; and it opens the door to explainability that is useful not only to the human, but to an agent.
This work has been partially supported by the AI4EUROPE (Grant agreement ID: 101070000), SoBigData PPP (Grant agreement ID: 101079043) and V. Giménez-Abalos fellowship within the “Generación D” initiative, Red.es, Ministerio para la Transformación Digital y de la Función Pública, for talent atraction (C005/24-ED CV1). Funded by the European Union NextGenerationEU funds, through PRTR.
Document Type: Conference object
File Description: application/pdf
Language: English
DOI: 10.5555/3709347.3743609
Rights: CC BY
Accession Number: edsair.dedup.wf.002..84a7236c462a2f81a623daf7d35ed8d0
Database: OpenAIRE
FullText Text:
  Availability: 0
Header DbId: edsair
DbLabel: OpenAIRE
An: edsair.dedup.wf.002..84a7236c462a2f81a623daf7d35ed8d0
RelevancyScore: 980
AccessLevel: 3
PubType: Conference
PubTypeId: conference
PreciseRelevancyScore: 979.736328125
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Policy graphs and intention: answering 'why' and 'how' from a telic perspective
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Giménez+Ábalos%2C+Víctor%22">Giménez Ábalos, Víctor</searchLink><br /><searchLink fieldCode="AR" term="%22Álvarez+Napagao%2C+Sergio%22">Álvarez Napagao, Sergio</searchLink><br /><searchLink fieldCode="AR" term="%22Tormos+Llorente%2C+Adrián%22">Tormos Llorente, Adrián</searchLink><br /><searchLink fieldCode="AR" term="%22Cortés+García%2C+Claudio+Ulises%22">Cortés García, Claudio Ulises</searchLink><br /><searchLink fieldCode="AR" term="%22Vázquez+Salceda%2C+Javier%22">Vázquez Salceda, Javier</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: UPCommons. Portal del coneixement obert de la UPC<br />Universitat Politècnica de Catalunya (UPC)
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2025.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Explainable+agency%22">Explainable agency</searchLink><br /><searchLink fieldCode="DE" term="%22Telic+explanations%22">Telic explanations</searchLink><br /><searchLink fieldCode="DE" term="%22XAI%22">XAI</searchLink><br /><searchLink fieldCode="DE" term="%22Post-hoc+explainability%22">Post-hoc explainability</searchLink><br /><searchLink fieldCode="DE" term="%22Àrees+temàtiques+de+la+UPC%3A%3AInformàtica%3A%3AIntel·ligència+artificial%3A%3AAgents+intel·ligents%22">Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Agents intel·ligents</searchLink><br /><searchLink fieldCode="DE" term="%22Interpretability%22">Interpretability</searchLink><br /><searchLink fieldCode="DE" term="%22Intentions%22">Intentions</searchLink><br /><searchLink fieldCode="DE" term="%22Reliability%22">Reliability</searchLink><br /><searchLink fieldCode="DE" term="%22Agent+explainability%22">Agent explainability</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Agents are a special kind of AI-based software in that they interact in complex environments and have increased potential for emergent behaviour. Explaining such behaviour is key to deploying trustworthy AI, but the increasing complexity and opaque nature of many agent implementations makes this hard. In this work, we reuse the Policy Graphs method --which can be used to explain opaque agent behaviour-- and enhance it to query it with hypotheses of desirable situations. These hypotheses are used to compute a numerical value to examine agent intentions at any particular moment, as a function of how likely the agent is to bring about a hypothesised desirable situation. We emphasise the relevance of how this approach has full epistemic traceability, and each belief used by the algorithms providing answers is backed by specific facts from its construction process. We show the numeric approach provides a robust and intuitive way to provide telic explainability (explaining current actions from the perspective of bringing about situations), and allows to evaluate the interpretability of behaviour of the agent based on the explanations; and it opens the door to explainability that is useful not only to the human, but to an agent.<br />This work has been partially supported by the AI4EUROPE (Grant agreement ID: 101070000), SoBigData PPP (Grant agreement ID: 101079043) and V. Giménez-Abalos fellowship within the “Generación D” initiative, Red.es, Ministerio para la Transformación Digital y de la Función Pública, for talent atraction (C005/24-ED CV1). Funded by the European Union NextGenerationEU funds, through PRTR.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Conference object
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.5555/3709347.3743609
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: CC BY
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsair.dedup.wf.002..84a7236c462a2f81a623daf7d35ed8d0
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsair&AN=edsair.dedup.wf.002..84a7236c462a2f81a623daf7d35ed8d0
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.5555/3709347.3743609
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Explainable agency
        Type: general
      – SubjectFull: Telic explanations
        Type: general
      – SubjectFull: XAI
        Type: general
      – SubjectFull: Post-hoc explainability
        Type: general
      – SubjectFull: Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Agents intel·ligents
        Type: general
      – SubjectFull: Interpretability
        Type: general
      – SubjectFull: Intentions
        Type: general
      – SubjectFull: Reliability
        Type: general
      – SubjectFull: Agent explainability
        Type: general
    Titles:
      – TitleFull: Policy graphs and intention: answering 'why' and 'how' from a telic perspective
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Giménez Ábalos, Víctor
      – PersonEntity:
          Name:
            NameFull: Álvarez Napagao, Sergio
      – PersonEntity:
          Name:
            NameFull: Tormos Llorente, Adrián
      – PersonEntity:
          Name:
            NameFull: Cortés García, Claudio Ulises
      – PersonEntity:
          Name:
            NameFull: Vázquez Salceda, Javier
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsair
            – Type: issn-locals
              Value: edsairFT
ResultId 1