Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/16986

Title: Rare neural correlations implement robotic conditioning with delayed rewards and disturbances
Authors: Soltoggio, Andrea
Lemme, Andre
Reinhart, Felix
Steil, Jochen
Keywords: Classical conditioning
Distal reward
Instrumental conditioning
Issue Date: 2013
Publisher: Frontiers Research Foundation
Citation: SOLTOGGIO, A. ... et al., 2013. Rare neural correlations implement robotic conditioning with delayed rewards and disturbances. Frontiers in Neurorobotics, 7.
Abstract: Neural conditioning associates cues and actions with following rewards. The environments in which robots operate, however, are pervaded by a variety of disturbing stimuli and uncertain timing. In particular, variable reward delays make it difficult to reconstruct which previous actions are responsible for following rewards. Such an uncertainty is handled by biological neural networks, but represents a challenge for computational models, suggesting the lack of a satisfactory theory for robotic neural conditioning. The present study demonstrates the use of rare neural correlations in making correct associations between rewards and previous cues or actions. Rare correlations are functional in selecting sparse synapses to be eligible for later weight updates if a reward occurs. The repetition of this process singles out the associating and reward-triggering pathways, and thereby copes with distal rewards. The neural network displays macro-level classical and operant conditioning, which is demonstrated in an interactive real-life human-robot interaction. The proposed mechanism models realistic conditioning in humans and animals and implements similar behaviors in neuro-robotic platforms.
Description: This is an open access article published under CC-BY licence. © the authors.
Sponsor: This work was supported by the European Community’s Seventh Framework Programme FP7/2007-2013, Challenge 2 Cognitive Systems, Interaction, Robotics (Grant agreement No. 248311-AMARSi).
Version: Published
DOI: 10.3389/fnbot.2013.00006
URI: https://dspace.lboro.ac.uk/2134/16986
Publisher Link: http://dx.doi.org/10.3389/fnbot.2013.00006
Appears in Collections:Published Articles (Computer Science)

Files associated with this item:

File Description SizeFormat
fnbot-07-00006.pdfPublished version2.06 MBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.