Publication:
Associative Search Network: A Reinforcement Learning Associative Memory

Simple item page
dc.contributor.authorBarto, Andrew G.
dc.contributor.authorSutton, Richard S.
dc.contributor.authorBrouwer, Peter S.
dc.contributor.departmentUniversity of Massachusetts - Amherst
dc.contributor.departmentUniversity of Massachusetts - Amherst
dc.contributor.departmentUniversity of Massachusetts - Amherst
dc.date2023-09-22T21:08:26.000
dc.date.accessioned2024-04-26T09:36:51Z
dc.date.available2024-04-26T09:36:51Z
dc.date.issued1981
dc.descriptionThis paper was harvested from CiteSeer
dc.description.abstractAn associative memory system is presented which does not require a "teacher" to provide the desired associations. For each input key it conducts a search for the output pattern which optimizes an external payoff or reinforcement signal. The associative search network (ASN) combines pattern recognition and function optimization capabilities in a simple and effective way. We define the associative search problem, discuss conditions under which the associative search network is capable of solving it, and present results from computer simulations. The synthesis of sensory-motor control surfaces is discussed as an example of the associative search problem.
dc.identifier.urihttps://hdl.handle.net/20.500.14394/10215
dc.relation.urlhttps://scholarworks.umass.edu/cgi/viewcontent.cgi?article=1019&context=cs_faculty_pubs&unstamped=1
dc.source.statuspublished
dc.subjectComputer Sciences
dc.titleAssociative Search Network: A Reinforcement Learning Associative Memory
dc.typearticle
dc.typearticle
digcom.contributor.authorBarto, Andrew G.
digcom.contributor.authorSutton, Richard S.
digcom.contributor.authorBrouwer, Peter S.
digcom.identifiercs_faculty_pubs/6
digcom.identifier.contextkey1298539
digcom.identifier.submissionpathcs_faculty_pubs/6
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Andrew_G_Barto_2.pdf
Size:
991.4 KB
Format:
Adobe Portable Document Format
Thumbnail Image
Name: Andrew_G_Barto_2.pdf
Size: 991.4 KB
Kind: Adobe PDF
Collections
Computer Science Department Faculty Publication Series