RL-KLM: Automating Keystroke-level Modeling with Reinforcement Learning

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Leino, Katri
dc.contributor.author Oulasvirta, Antti
dc.contributor.author Kurimo, Mikko
dc.date.accessioned 2019-06-03T14:17:16Z
dc.date.available 2019-06-03T14:17:16Z
dc.date.issued 2019
dc.identifier.citation Leino , K , Oulasvirta , A & Kurimo , M 2019 , RL-KLM: Automating Keystroke-level Modeling with Reinforcement Learning . in 24th International Conference on Intelligent User Interfaces (IUI ’19) . ACM , pp. 476-480 , International Conference on Intelligent User Interfaces , Los Angeles , United States , 16/03/2019 . https://doi.org/10.1145/3301275.3302285 en
dc.identifier.isbn 978-1-4503-6272-6
dc.identifier.other PURE UUID: b0f0ba0f-78b9-4953-91a9-33958047f827
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/rlklm-automating-keystrokelevel-modeling-with-reinforcement-learning(b0f0ba0f-78b9-4953-91a9-33958047f827).html
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=85065567360&partnerID=8YFLogxK
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/34076579/ELEC_Leino_RL_KLM_HCI.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/38348
dc.description | openaire: EC/H2020/637991/EU//COMPUTED
dc.description.abstract The Keystroke-Level Model (KLM) is a popular model for predicting users’ task completion times with graphical user interfaces. KLM predicts task completion times as a linear function of elementary operators. However, the policy, or the assumed sequence of the operators that the user executes, needs to be prespecified by the analyst. This paper investigates Reinforcement Learning (RL) as an algorithmic method to obtain the policy automatically. We define the KLM as an Markov Decision Process, and show that when solved with RL methods, this approach yields user-like policies in simple but realistic interaction tasks. RL-KLM offers a quick way to obtain a global upper bound for user performance. It opens up new possibilities to use KLM in computational interaction. However, scalability and validity remain open issues. en
dc.format.extent 5
dc.format.extent 476-480
dc.format.mimetype application/pdf
dc.language.iso en en
dc.relation info:eu-repo/grantAgreement/EC/H2020/637991/EU//COMPUTED
dc.relation.ispartof International Conference on Intelligent User Interfaces en
dc.relation.ispartofseries 24th International Conference on Intelligent User Interfaces (IUI ’19) en
dc.rights openAccess en
dc.subject.other 113 Computer and information sciences en
dc.title RL-KLM: Automating Keystroke-level Modeling with Reinforcement Learning en
dc.type A4 Artikkeli konferenssijulkaisussa fi
dc.description.version Peer reviewed en
dc.contributor.department Department of Signal Processing and Acoustics
dc.contributor.department Helsinki Institute for Information Technology HIIT
dc.contributor.department Centre of Excellence in Computational Inference, COIN
dc.contributor.department Department of Communications and Networking en
dc.subject.keyword Keystroke-level modelling
dc.subject.keyword Reinforcement Learning
dc.subject.keyword Computational evaluation
dc.subject.keyword Computational design
dc.subject.keyword 113 Computer and information sciences
dc.identifier.urn URN:NBN:fi:aalto-201906033433
dc.identifier.doi 10.1145/3301275.3302285
dc.type.version publishedVersion

Files in this item

Files Size Format View

There are no open access files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive

Advanced Search

article-iconSubmit a publication