Please use this identifier to cite or link to this item:https://hdl.handle.net/20.500.12259/47460
Type of publication: research article
Type of publication (PDB): Straipsnis konferencijos medžiagoje kitose duomenų bazėse / Article in conference proceedings in other databases (P1c)
Field of Science: Informatika / Informatics (N009)
Author(s): Kolodziejski, Christoph;Porr, Bernd;Tamošiūnaitė, Minija;Wörgötter, Florentin
Title: On the asymptotic equivalence between differential Hebbian and temporal difference learning using a local third factor
Is part of: Advances in neural information processing systems 21 : 22nd annual conference on neural information processing systems, Vancouver, British Columbia, Canada, December 8-11, 2008 : proceedings. Red Hook, NY : Curran, 2009
Extent: p. 857-864
Date: 2009
Keywords: Hebbian learning;Temporal difference;Third factor
ISBN: 9781605609492
Abstract: In this theoretical contribution we provide mathematical proof that two of the most important classes of network learning - correlation-based differential Hebbian learning and reward-based temporal difference learning - are asymptotically equivalent when timing the learning with a localmodulatory signal. This opens the opportunity to consistently reformulate most of the abstract reinforcement learning framework from a correlation based perspective that is more closely related to the biophysics of neurons
Internet: http://books.nips.cc/papers/files/nips21/NIPS2008_0291.pdf
Affiliation(s): Taikomosios informatikos katedra
Vytauto Didžiojo universitetas
Appears in Collections:Universiteto mokslo publikacijos / University Research Publications

Files in This Item:
marc.xml8.07 kBXMLView/Open

MARC21 XML metadata

Show full item record
Export via OAI-PMH Interface in XML Formats
Export to Other Non-XML Formats


CORE Recommender

Page view(s)

76
checked on May 1, 2021

Download(s)

8
checked on May 1, 2021

Google ScholarTM

Check

Altmetric


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