Show simple item record

dc.contributor.authorVoudouris, K
dc.contributor.authorDonnelly, N
dc.contributor.authorRutar, D
dc.contributor.authorBurnell, R
dc.contributor.authorBurden, J
dc.contributor.authorHernández-Orallo, J
dc.contributor.authorCheke, LG
dc.date.accessioned2022-11-11T09:16:29Z
dc.date.issued2022-07-25
dc.date.updated2022-11-10T17:04:47Z
dc.description.abstractObject permanence, the understanding and belief that objects continue to exist even when they are not directly observable, is important for any agent interacting with the world. Psychologists have been studying object permanence in animals for at least 50 years, and in humans for almost 50 more. In this paper, we apply the methodologies from psychology and cognitive science to present a novel testbed for evaluating whether artificial agents have object permanence. Built in the Animal-AI environment, Object-Permanence In Animal-Ai: GEneralisable Test Suites (O-PIAAGETS) improves on other benchmarks for assessing object permanence in terms of both size and validity. We discuss the layout of O-PIAAGETS and how it can be used to robustly evaluate OP in embodied agents.en_GB
dc.description.sponsorshipFuture of Life Institute (FLI)en_GB
dc.description.sponsorshipEuropean Union’s Horizon 2020en_GB
dc.description.sponsorshipDARPAen_GB
dc.description.sponsorshipEconomic and Social Research Councilen_GB
dc.identifier.citationEBeM’22: Workshop on AI Evaluation Beyond Metrics, July 25, 2022, Vienna, Austriaen_GB
dc.identifier.grantnumberRFP2-152en_GB
dc.identifier.grantnumber952215 (TAILOR)en_GB
dc.identifier.grantnumberHR00112120007 (RECoGAI)en_GB
dc.identifier.grantnumberES/P000738/1en_GB
dc.identifier.otherCEUR-WS.org/Vol-3169/paper2.pdf
dc.identifier.urihttp://hdl.handle.net/10871/131738
dc.language.isoenen_GB
dc.publisherCEUR Workshop Proceedingsen_GB
dc.rights© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)en_GB
dc.subjectObject Permanenceen_GB
dc.subjectAI Evaluationen_GB
dc.subjectEmbodied Agentsen_GB
dc.subjectAnimal-AI Environmenten_GB
dc.subjectDevelopmental Psychologyen_GB
dc.subjectComparative Cognitionen_GB
dc.titleEvaluating object permanence in embodied agents using the animal-AI environmenten_GB
dc.typeConference paperen_GB
dc.date.available2022-11-11T09:16:29Z
dc.identifier.issn1613-0073
exeter.locationVienna, Austria
dc.descriptionThis is the final version. Available from CEUR Workshop Proceedings via the URL in this record. en_GB
dc.relation.ispartofhttps://ceur-ws.org/Vol-3169/paper2.pdf
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/en_GB
rioxxterms.versionVoRen_GB
rioxxterms.licenseref.startdate2022-07-25
rioxxterms.typeConference Paper/Proceeding/Abstracten_GB
refterms.dateFCD2022-11-11T09:11:11Z
refterms.versionFCDVoR
refterms.dateFOA2022-11-11T09:16:33Z
refterms.panelBen_GB
refterms.dateFirstOnline2022-07-25
pubs.name-of-conferenceWorkshop on AI Evaluation Beyond Metrics at IJCAI-ECAI 2022.


Files in this item

This item appears in the following Collection(s)

Show simple item record

© 2022 Copyright for this paper by its authors. Use permitted under Creative
Commons License Attribution 4.0 International (CC BY 4.0)
Except where otherwise noted, this item's licence is described as © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0)