Rare neural correlations implement robotic conditioning with reward delays and disturbances

Soltoggio A, Lemme A, Reinhart F, Steil JJ (2013)
Frontiers in Neurorobotics 7: 6.

Download
OA
Zeitschriftenaufsatz | Veröffentlicht | Englisch
Abstract / Bemerkung
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.
Stichworte
Erscheinungsjahr
Zeitschriftentitel
Frontiers in Neurorobotics
Band
7
Seite
6
ISSN
eISSN
Finanzierungs-Informationen
Article Processing Charge funded by the Deutsche Forschungsgemeinschaft and the Open Access Publication Fund of Bielefeld University.
PUB-ID

Zitieren

Soltoggio A, Lemme A, Reinhart F, Steil JJ. Rare neural correlations implement robotic conditioning with reward delays and disturbances. Frontiers in Neurorobotics. 2013;7:6.
Soltoggio, A., Lemme, A., Reinhart, F., & Steil, J. J. (2013). Rare neural correlations implement robotic conditioning with reward delays and disturbances. Frontiers in Neurorobotics, 7, 6. doi:10.3389/fnbot.2013.00006
Soltoggio, A., Lemme, A., Reinhart, F., and Steil, J. J. (2013). Rare neural correlations implement robotic conditioning with reward delays and disturbances. Frontiers in Neurorobotics 7, 6.
Soltoggio, A., et al., 2013. Rare neural correlations implement robotic conditioning with reward delays and disturbances. Frontiers in Neurorobotics, 7, p 6.
A. Soltoggio, et al., “Rare neural correlations implement robotic conditioning with reward delays and disturbances”, Frontiers in Neurorobotics, vol. 7, 2013, pp. 6.
Soltoggio, A., Lemme, A., Reinhart, F., Steil, J.J.: Rare neural correlations implement robotic conditioning with reward delays and disturbances. Frontiers in Neurorobotics. 7, 6 (2013).
Soltoggio, Andrea, Lemme, Andre, Reinhart, Felix, and Steil, Jochen J. “Rare neural correlations implement robotic conditioning with reward delays and disturbances”. Frontiers in Neurorobotics 7 (2013): 6.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2013-04-16T11:47:40Z

8 Zitationen in Europe PMC

Daten bereitgestellt von Europe PubMed Central.

RM-SORN: a reward-modulated self-organizing recurrent neural network.
Aswolinskiy W, Pipa G., Front Comput Neurosci 9(), 2015
PMID: 25852533
Self-organizing neural integration of pose-motion features for human action recognition.
Parisi GI, Weber C, Wermter S., Front Neurorobot 9(), 2015
PMID: 26106323
Editorial: Neural plasticity for rich and uncertain robotic information streams.
Soltoggio A, van der Velde F., Front Neurorobot 9(), 2015
PMID: 26578947
Value and reward based learning in neurorobots.
Krichmar JL, Röhrbein F., Front Neurorobot 7(), 2013
PMID: 24062683

57 References

Daten bereitgestellt von Europe PubMed Central.


Sutton R., Barto A.., 1998

Thorndike E.., 1911
iCub – the design and realization of an open humanoid platform for cognitive and neuroscience research
Tsakarakis N., Metta G., Sandini G., Vernon D., Beira R., Becchi F.., 2007
Spike-based reinforcement learning in continuous state and action space: when policy gradient methods fail.
Vasilaki E, Fremaux N, Urbanczik R, Senn W, Gerstner W., PLoS Comput. Biol. 5(12), 2009
PMID: 19997492
Coincidence detection in single dendritic spines mediated by calcium release.
Wang SS, Denk W, Hausser M., Nat. Neurosci. 3(12), 2000
PMID: 11100147
The psychology and neuroscience of forgetting.
Wixted JT., Annu Rev Psychol 55(), 2004
PMID: 14744216
Neuromodulation of reactive sensorimotor mappings as short-term memory mechanism in delayed response tasks
Ziemke T., Thieme M.., 2002

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 23565092
PubMed | Europe PMC

Suchen in

Google Scholar