his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
Improving Robot Motor Learning with Negatively Valenced Reinforcement Signals
Knowledge Technology, Informatics Department, University of Hamburg, Hamburg, Germany.
University of Skövde, School of Informatics. University of Skövde, The Informatics Research Centre. Division of Cognition and Communication, Department of Applied IT, University of Gothenburg, Gothenburg, Sweden. (Interaction Lab)
Knowledge Technology, Informatics Department, University of Hamburg, Hamburg, Germany.
2017 (English)In: Frontiers in Neurorobotics, ISSN 1662-5218, Vol. 11, 10Article in journal (Refereed) Published
Abstract [en]

Both nociception and punishment signals have been used in robotics. However, the potential for using these negatively valenced types of reinforcement learning signals for robot learning has not been exploited in detail yet. Nociceptive signals are primarily used as triggers of preprogrammed action sequences. Punishment signals are typically disembodied, i. e., with no or little relation to the agent-intrinsic limitations, and they are often used to impose behavioral constraints. Here, we provide an alternative approach for nociceptive signals as drivers of learning rather than simple triggers of preprogrammed behavior. Explicitly, we use nociception to expand the state space while we use punishment as a negative reinforcement learning signal. We compare the performance-in terms of task error, the amount of perceived nociception, and length of learned action sequences-of different neural networks imbued with punishment-based reinforcement signals for inverse kinematic learning. We contrast the performance of a version of the neural network that receives nociceptive inputs to that without such a process. Furthermore, we provide evidence that nociception can improve learning-making the algorithm more robust against network initializations-as well as behavioral performance by reducing the task error, perceived nociception, and length of learned action sequences. Moreover, we provide evidence that punishment, at least as typically used within reinforcement learning applications, may be detrimental in all relevant metrics.

Place, publisher, year, edition, pages
Frontiers Media S.A., 2017. Vol. 11, 10
Keyword [en]
reinforcement learning, inverse kinematics, nociception, punishment, self-protective mechanisms
National Category
Computer and Information Science
Research subject
Interaction Lab (ILAB)
Identifiers
URN: urn:nbn:se:his:diva-13548DOI: 10.3389/fnbot.2017.00010ISI: 000399141900001PubMedID: 28420976Scopus ID: 2-s2.0-85018457189OAI: oai:DiVA.org:his-13548DiVA: diva2:1093360
Available from: 2017-05-05 Created: 2017-05-05 Last updated: 2017-09-12Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textPubMedScopus

Search in DiVA

By author/editor
Lowe, Robert J.
By organisation
School of InformaticsThe Informatics Research Centre
In the same journal
Frontiers in Neurorobotics
Computer and Information Science

Search outside of DiVA

GoogleGoogle Scholar

Altmetric score

Total: 62 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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