Connecting the Demons: How connection choices of a Horde implementation affect Demon prediction capabilities.

Simple item page
dc.contributor.advisorOtterlo, M. van
dc.contributor.advisorSprinkhuizen-Kuyper, I.G.
dc.contributor.authorWaa, J.S. van der
dc.date.issued2013-08-26
dc.description.abstractThe reinforcement learning framework Horde, developed by Sutton et al. [9], is a network of Demons that processes sensorimotor data to general knowledge about the world. These Demons can be connected to each other and to data-streams from specific sensors. This paper will focus on how and if the capability of Demons to learn general knowledge is affected by different numbers of connections with both other Demons and sensors. Several experiments and tests where done and analyzed to map these effects and to provide insight in how these effects arose. Keywords: Artificial Intelligence, value function approximation, temporal difference learning, reinforcement learning, predictions, prediction error, pendulum environment, parallel processing, offpolicy learning, network connections, knowledge representation, Horde Architecture, GQ( ), general value functionsen_US
dc.identifier.urihttp://theses.ubn.ru.nl/handle/123456789/137
dc.language.isoenen_US
dc.thesis.facultyFaculteit der Sociale Wetenschappenen_US
dc.thesis.specialisationBachelor Artificial Intelligenceen_US
dc.thesis.studyprogrammeArtificial Intelligenceen_US
dc.thesis.typeBacheloren_US
dc.titleConnecting the Demons: How connection choices of a Horde implementation affect Demon prediction capabilities.en_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Waa van der J,BA_2013.pdf
Size:
2.09 MB
Format:
Adobe Portable Document Format
Description:
Scriptietekst
Download
Collections
Faculteit der Sociale Wetenschappen