Change search
ReferencesLink to record
Permanent link

Direct link
Learning Predictive State Representations for Planning
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.
KTH, School of Computer Science and Communication (CSC), Computer Vision and Active Perception, CVAP. KTH, School of Computer Science and Communication (CSC), Centres, Centre for Autonomous Systems, CAS.ORCID iD: 0000-0003-2965-2953
2015 (English)In: 2015 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), IEEE Press, 2015, 3427-3434 p.Conference paper (Refereed)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.

Place, publisher, year, edition, pages
IEEE Press, 2015. 3427-3434 p.
Series
, IEEE International Conference on Intelligent Robots and Systems, ISSN 2153-0858
National Category
Computer Vision and Robotics (Autonomous Systems)
Identifiers
URN: urn:nbn:se:kth:diva-185107DOI: 10.1109/IROS.2015.7353855ISI: 000371885403089ScopusID: 2-s2.0-84958177858ISBN: 978-1-4799-9994-1OAI: oai:DiVA.org:kth-185107DiVA: diva2:919033
Conference
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), SEP 28-OCT 02, 2015, Hamburg, GERMANY
Note

QC 20160412

Available from: 2016-04-12 Created: 2016-04-11 Last updated: 2016-04-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Stork, Johannes A.Ek, Carl HenrikKragic, Danica
By organisation
Computer Vision and Active Perception, CVAPCentre for Autonomous Systems, CAS
Computer Vision and Robotics (Autonomous Systems)

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 7 hits
ReferencesLink to record
Permanent link

Direct link