Object-model transfer in the general video game domain

dc.contributor.advisorMiikkulainen, Risto
dc.creatorBraylan, Alexander Eric
dc.creator.orcid0000-0002-7404-8707
dc.date.accessioned2019-09-27T14:28:39Z
dc.date.available2019-09-27T14:28:39Z
dc.date.created2019-08
dc.date.issued2019-09-17
dc.date.submittedAugust 2019
dc.date.updated2019-09-27T14:28:40Z
dc.description.abstractReinforcement learning agents often benefit from learning models that predict their environment. However, learned models may not generalize well to novel situations. This thesis investigates the potential for a transfer learning approach to address the challenge in the video game domain. The approach helps agents learn models of new games by transferring knowledge from previously learned games. Transfer is facilitated by decomposing games into the objects they contain. The assumption is that it is easier to relate features between objects from different games than features between whole environments of different games. Experiments show that predictions made by this method are more accurate than predictions made without transferred knowledge, and this improvement is demonstrated to result in increased efficiency in a task where an agent explores a maze-like game. The conclusion is that model learning can be enhanced by transferring object models from previously learned environments.
dc.description.departmentComputer Sciences
dc.format.mimetypeapplication/pdf
dc.identifier.urihttps://hdl.handle.net/2152/76040
dc.identifier.urihttp://dx.doi.org/10.26153/tsw/3139
dc.language.isoen
dc.subjectModel learning
dc.subjectReinforcement learning
dc.subjectTransfer learning
dc.subjectVideo game playing
dc.titleObject-model transfer in the general video game domain
dc.typeThesis
dc.type.materialtext
thesis.degree.departmentComputer Sciences
thesis.degree.disciplineComputer Science
thesis.degree.grantorThe University of Texas at Austin
thesis.degree.levelMasters
thesis.degree.nameMaster of Science in Computer Sciences

Access full-text files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
BRAYLAN-THESIS-2019.pdf
Size:
762.05 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 2 of 2
No Thumbnail Available
Name:
PROQUEST_LICENSE.txt
Size:
4.46 KB
Format:
Plain Text
Description:
No Thumbnail Available
Name:
LICENSE.txt
Size:
1.85 KB
Format:
Plain Text
Description: