Reinforcement learning with attention that works: a self-supervised approach

Simple item page
dc.contributor.authorManchin, A.
dc.contributor.authorAbbasnejad, E.
dc.contributor.authorVan Den Hengel, A.
dc.contributor.conferenceInternational Conference on Neural Information Processing (ICONIP) (12 Dec 2019 - 15 Dec 2019 : Sydney, Australia)
dc.contributor.editorGedeon, T.
dc.contributor.editorWong, K.W.
dc.contributor.editorLee, M.
dc.date.issued2019
dc.description.abstractAttention models have had a significant positive impact on deep learning across a range of tasks. However previous attempts at integrating attention with reinforcement learning have failed to produce significant improvements. Unlike the selective attention models used in previous attempts, which constrain the attention via preconceived notions of importance, our implementation utilises the Markovian properties inherent in the state input. We propose the first combination of self attention and reinforcement learning that is capable of producing significant improvements, including new state of the art results in the Arcade Learning Environment.
dc.description.statementofresponsibilityAnthony Manchin, Ehsan Abbasnejad, and Anton van den Hengel
dc.identifier.citationCommunications in Computer and Information Science, 2019 / Gedeon, T., Wong, K.W., Lee, M. (ed./s), vol.1143 CCIS, pp.223-230
dc.identifier.doi10.1007/978-3-030-36802-9_25
dc.identifier.isbn9783030368012
dc.identifier.issn1865-0929
dc.identifier.issn1865-0937
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]
dc.identifier.urihttp://hdl.handle.net/2440/123724
dc.language.isoen
dc.publisherSpringer
dc.publisher.placeSwitzerland
dc.relation.ispartofseriesCommunications in Computer and Information Science; 1143
dc.rights© Springer Nature Switzerland AG 2019
dc.source.urihttps://doi.org/10.1007/978-3-030-36802-9_25
dc.subjectReinforcement learning; Attention; Deep learning
dc.titleReinforcement learning with attention that works: a self-supervised approach
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Australian Institute for Machine Learning publications