University of Aberdeen logo

AURA - Aberdeen University Research Archive

 

Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation

Simple item page
dc.contributor.authorDai, Tianhong
dc.contributor.authorArulkumaran, Kai
dc.contributor.authorGerbert, Tamara
dc.contributor.authorTukra, Samyakh
dc.contributor.authorBehbahani, Feryal
dc.contributor.authorBharath, Anil Anthony
dc.contributor.institutionUniversity of Aberdeen.Machine Learningen
dc.contributor.institutionUniversity of Aberdeen.Computing Scienceen
dc.date.accessioned2022-12-08T21:38:01Z
dc.date.available2022-12-08T21:38:01Z
dc.date.issued2022-07-07
dc.description.statusPeer revieweden
dc.format.extent23
dc.format.extent10620447
dc.identifier221357000
dc.identifier8e4d12ba-5fee-44e0-8dd7-1d9ccd350c6e
dc.identifier85128457623
dc.identifier.citationDai, T, Arulkumaran, K, Gerbert, T, Tukra, S, Behbahani, F & Bharath, A A 2022, 'Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation', Neurocomputing, vol. 493, pp. 143-165. https://doi.org/10.1016/j.neucom.2022.04.005en
dc.identifier.doi10.1016/j.neucom.2022.04.005
dc.identifier.issn0925-2312
dc.identifier.otherORCID: /0000-0001-8904-1551/work/122287634
dc.identifier.otherBibtex: DAI2022143
dc.identifier.urihttps://hdl.handle.net/2164/19707
dc.identifier.urlhttp://dx.doi.org/10.1016/j.neucom.2022.04.005en
dc.identifier.vol493en
dc.language.isoeng
dc.relation.ispartofNeurocomputingen
dc.subjectDeep reinforcement learningen
dc.subjectGeneralisationen
dc.subjectInterpretabilityen
dc.subjectSaliencyen
dc.subjectQA75 Electronic computers. Computer scienceen
dc.subject.lccQA75en
dc.titleAnalysing Deep Reinforcement Learning Agents Trained with Domain Randomisationen
dc.typeJournal articleen

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
Dai_etal_Analysing_deep_reinforcement_VOR.pdf
Size:
10.13 MB
Format:
Adobe Portable Document Format
Download

Collections

All research