Show simple item record

dc.contributor.authorDuque Van Hissenhoven, Juan Agustin
dc.date.accessioned2019-02-12T14:42:59Z
dc.date.available2019-02-12T14:42:59Z
dc.date.created2018-12
dc.date.submittedDecember 2018
dc.identifier.urihttp://hdl.handle.net/1853/60889
dc.description.abstractWe intend to develop a framework that allows to determine sub goals for hierarchical reinforcement learning tasks in an unsupervised manner. The motivation for this research project is to make hierarchical reinforcement learning algorithms independent of human input (i.e. the sub goals, which must be handpicked by the algorithm designers). It would be interesting to determine whether the unsupervised goal determination converges towards the optimal solution and has any impact in the running performance of the algorithm. To create these sub goals, we will discretize the state space of the problem up to a given granularity and create an adjacency matrix between clusters over which we can then utilize spectral graph partitioning to determine the goals.
dc.format.mimetypeapplication/pdf
dc.language.isoen_US
dc.publisherGeorgia Institute of Technology
dc.subjectHierarchical reinforcement learning
dc.subjectSpectral graph partitioning
dc.titleUnsupervised State-space Decomposition in Hierarchical Reinforcement Learning
dc.typeUndergraduate Research Option Thesis
dc.description.degreeUndergraduate
dc.contributor.departmentComputer Science
thesis.degree.levelUndergraduate
dc.contributor.committeeMemberWilson, Tobias
dc.date.updated2019-02-12T14:42:59Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record