Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Teaching robots behavior patterns by using reinforcement learning - How to raise pet robots with a remote control
KTH, Superseded Departments, Numerical Analysis and Computer Science, NADA.
2004 (English)In: SICE 2004 Annual Conference, Vols 1-3, 2004, 143-146 p.Conference paper, Published paper (Refereed)
Abstract [en]

The goal of this project was to show that complex behavior patterns can be learnt by a system based on reinforcement learning. The specific task was to make AIBO, the Sony robot dog, learn complex behavior patterns based on interactions between humans and AEBO. The reinforcement learning system is taught by remote control, used by the human and connected to AIBO. To remember the learnt behavior sequences, a short-term memory of prior actions is used by AIBO. This paper demonstrates that it is possible to learn behavior sequences and the relationship of cause and effect in complex environments. The paper also shows that the system works in a natural environment, based on the interaction between humans and AIBO, learning the rewards and the means to reach them in parallel. AIBO is also able to pick up new behaviors instantly by using a method we call 'Instant learning'. The paper presents the methods for implementing such a system.

Place, publisher, year, edition, pages
2004. 143-146 p.
Keyword [en]
learning, remote control user demonstration, AIBO
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:kth:diva-44325ISI: 000231324800028Scopus ID: 2-s2.0-12744254963ISBN: 4-907764-22-7 (print)OAI: oai:DiVA.org:kth-44325DiVA: diva2:451093
Conference
SICE 2004 Annual Conference Location: Sapporo, JAPAN Date: AUG 04-06, 2005
Note

QC 20111024

Available from: 2011-10-24 Created: 2011-10-20 Last updated: 2014-12-15Bibliographically approved

Open Access in DiVA

No full text

Scopus

Search in DiVA

By author/editor
Ullerstam, Måns
By organisation
Numerical Analysis and Computer Science, NADA
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetric score

isbn
urn-nbn
Total: 30 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf