A reinforcement learning approach to synthesizing climbing movements

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.author Naderi, Kourosh
dc.contributor.author Babadi, Amin
dc.contributor.author Roohi, Shaghayegh
dc.contributor.author Hamalainen, Perttu
dc.date.accessioned 2019-11-07T12:10:06Z
dc.date.available 2019-11-07T12:10:06Z
dc.date.issued 2019-08-01
dc.identifier.citation Naderi , K , Babadi , A , Roohi , S & Hamalainen , P 2019 , A reinforcement learning approach to synthesizing climbing movements . in IEEE Conference on Games 2019, CoG 2019 . , 8848127 , IEEE Conference on Computatonal Intelligence and Games , vol. 2019-August , IEEE COMPUTER SOCIETY PRESS , IEEE Conference on Games , London , United Kingdom , 20/08/2019 . https://doi.org/10.1109/CIG.2019.8848127 en
dc.identifier.isbn 9781728118840
dc.identifier.issn 2325-4270
dc.identifier.issn 2325-4289
dc.identifier.other PURE UUID: fa2fbe51-f179-4efd-9c4f-fe325b19ffc7
dc.identifier.other PURE ITEMURL: https://research.aalto.fi/en/publications/a-reinforcement-learning-approach-to-synthesizing-climbing-movements(fa2fbe51-f179-4efd-9c4f-fe325b19ffc7).html
dc.identifier.other PURE LINK: http://www.scopus.com/inward/record.url?scp=85073095268&partnerID=8YFLogxK
dc.identifier.other PURE FILEURL: https://research.aalto.fi/files/38172752/SCI_Naderi_A_Reinforcement.2019.pdf
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/41196
dc.description.abstract This paper addresses the problem of synthesizing simulated humanoid climbing movements given the target holds, e.g., by the player of a climbing game. We contribute the first deep reinforcement learning solution that can handle interactive physically simulated humanoid climbing with more than one limb switching holds at the same time. A key component of our approach is Self-Supervised Episode State Initialization (SS- ESI), which ensures diverse exploration and speeds up learning, compared to a baseline approach where the climber is reset to an initial pose after failure. Our results also show that training with a multi-step action parameterization can produce both smoother movements and enable learning from slightly fewer explored actions at the cost of increased simulation time per action. en
dc.format.extent 7
dc.format.mimetype application/pdf
dc.language.iso en en
dc.publisher IEEE
dc.relation.ispartof IEEE Conference on Games en
dc.relation.ispartofseries IEEE Conference on Games 2019, CoG 2019 en
dc.relation.ispartofseries IEEE Conference on Computatonal Intelligence and Games en
dc.relation.ispartofseries Volume 2019-August en
dc.rights openAccess en
dc.subject.other Artificial Intelligence en
dc.subject.other Computer Graphics and Computer-Aided Design en
dc.subject.other Computer Vision and Pattern Recognition en
dc.subject.other Human-Computer Interaction en
dc.subject.other Software en
dc.subject.other 113 Computer and information sciences en
dc.title A reinforcement learning approach to synthesizing climbing movements en
dc.type A4 Artikkeli konferenssijulkaisussa fi
dc.description.version Peer reviewed en
dc.contributor.department Professorship Hämäläinen P.
dc.contributor.department Department of Computer Science
dc.contributor.department Department of Computer Science en
dc.contributor.department Department of Media en
dc.subject.keyword Action parameterization
dc.subject.keyword Climbing movements
dc.subject.keyword Reinforcement learning
dc.subject.keyword State initialization
dc.subject.keyword Artificial Intelligence
dc.subject.keyword Computer Graphics and Computer-Aided Design
dc.subject.keyword Computer Vision and Pattern Recognition
dc.subject.keyword Human-Computer Interaction
dc.subject.keyword Software
dc.subject.keyword 113 Computer and information sciences
dc.identifier.urn URN:NBN:fi:aalto-201911076201
dc.identifier.doi 10.1109/CIG.2019.8848127
dc.type.version acceptedVersion


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

Browse