Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • 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
Vpe: Variational policy embedding for transfer reinforcement learning
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.ORCID-id: 0000-0001-6824-6443
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL.ORCID-id: 0000-0003-2965-2953
KTH, Skolan för elektroteknik och datavetenskap (EECS), Intelligenta system, Robotik, perception och lärande, RPL. Center for Applied Autonomous Sensor Systems, Örebro University, Sweden.ORCID-id: 0000-0003-3958-6179
2019 (engelsk)Inngår i: 2019 International Conference on Robotics And Automation (ICRA), Institute of Electrical and Electronics Engineers (IEEE), 2019, s. 36-42Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Reinforcement Learning methods are capable of solving complex problems, but resulting policies might perform poorly in environments that are even slightly different. In robotics especially, training and deployment conditions often vary and data collection is expensive, making retraining undesirable. Simulation training allows for feasible training times, but on the other hand suffer from a reality-gap when applied in real-world settings. This raises the need of efficient adaptation of policies acting in new environments. We consider the problem of transferring knowledge within a family of similar Markov decision processes. We assume that Q-functions are generated by some low-dimensional latent variable. Given such a Q-function, we can find a master policy that can adapt given different values of this latent variable. Our method learns both the generative mapping and an approximate posterior of the latent variables, enabling identification of policies for new tasks by searching only in the latent space, rather than the space of all policies. The low-dimensional space, and master policy found by our method enables policies to quickly adapt to new environments. We demonstrate the method on both a pendulum swing-up task in simulation, and for simulation-to-real transfer on a pushing task.

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2019. s. 36-42
Serie
IEEE International Conference on Robotics and Automation ICRA, ISSN 1050-4729
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-258072DOI: 10.1109/ICRA.2019.8793556ISI: 000494942300006Scopus ID: 2-s2.0-85071508761ISBN: 9781538660263 (tryckt)OAI: oai:DiVA.org:kth-258072DiVA, id: diva2:1349756
Konferanse
2019 International Conference on Robotics and Automation, ICRA 2019; Palais des Congres de Montreal, Montreal; Canada; 20 May 2019 through 24 May 2019
Prosjekter
Factories of the Future (FACT)
Merknad

QC 20190916

Tilgjengelig fra: 2019-09-09 Laget: 2019-09-09 Sist oppdatert: 2020-01-31bibliografisk kontrollert

Open Access i DiVA

fulltext(1920 kB)62 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 1920 kBChecksum
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopusConference webpage

Personposter BETA

Kragic, DanicaStork, Johannes A.

Søk i DiVA

Av forfatter/redaktør
Arnekvist, IsacKragic, DanicaStork, Johannes A.
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 62 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
isbn
urn-nbn

Altmetric

doi
isbn
urn-nbn
Totalt: 212 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • 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