Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Learning Predictive State Representations for Planning
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.
KTH, Skolan för datavetenskap och kommunikation (CSC), Datorseende och robotik, CVAP. KTH, Skolan för datavetenskap och kommunikation (CSC), Centra, Centrum för Autonoma System, CAS.ORCID-id: 0000-0003-2965-2953
2015 (engelsk)Inngår i: 2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), IEEE Press, 2015, s. 3427-3434Konferansepaper, Publicerat paper (Fagfellevurdert)
Resurstyp
Text
Abstract [en]

Predictive State Representations (PSRs) allow modeling of dynamical systems directly in observables and without relying on latent variable representations. A problem that arises from learning PSRs is that it is often hard to attribute semantic meaning to the learned representation. This makes generalization and planning in PSRs challenging. In this paper, we extend PSRs and introduce the notion of PSRs that include prior information (P-PSRs) to learn representations which are suitable for planning and interpretation. By learning a low-dimensional embedding of test features we map belief points of similar semantic to the same region of a subspace. This facilitates better generalization for planning and semantical interpretation of the learned representation. In specific, we show how to overcome the training sample bias and introduce feature selection such that the resulting representation emphasizes observables related to the planning task. We show that our P-PSRs result in qualitatively meaningful representations and present quantitative results that indicate improved suitability for planning.

sted, utgiver, år, opplag, sider
IEEE Press, 2015. s. 3427-3434
Serie
IEEE International Conference on Intelligent Robots and Systems, ISSN 2153-0858
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-185107DOI: 10.1109/IROS.2015.7353855ISI: 000371885403089Scopus ID: 2-s2.0-84958177858ISBN: 978-1-4799-9994-1 (tryckt)OAI: oai:DiVA.org:kth-185107DiVA, id: diva2:919033
Konferanse
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), SEP 28-OCT 02, 2015, Hamburg, GERMANY
Merknad

QC 20160412

Tilgjengelig fra: 2016-04-12 Laget: 2016-04-11 Sist oppdatert: 2018-01-10bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Andre lenker

Forlagets fulltekstScopus

Personposter BETA

Kragic, Danica

Søk i DiVA

Av forfatter/redaktør
Stork, Johannes A.Ek, Carl HenrikKragic, Danica
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 35 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf