Title:
Unsupervised State-space Decomposition in Hierarchical Reinforcement Learning

Simple item page
dc.contributor.author Duque Van Hissenhoven, Juan Agustin
dc.contributor.committeeMember Wilson, Tobias
dc.contributor.department Computer Science
dc.date.accessioned 2019-02-12T14:42:59Z
dc.date.available 2019-02-12T14:42:59Z
dc.date.created 2018-12
dc.date.issued 2018-12
dc.date.submitted December 2018
dc.date.updated 2019-02-12T14:42:59Z
dc.description.abstract We 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.description.degree Undergraduate
dc.format.mimetype application/pdf
dc.identifier.uri http://hdl.handle.net/1853/60889
dc.language.iso en_US
dc.publisher Georgia Institute of Technology
dc.subject Hierarchical reinforcement learning
dc.subject Spectral graph partitioning
dc.title Unsupervised State-space Decomposition in Hierarchical Reinforcement Learning
dc.type Text
dc.type.genre Undergraduate Thesis
dspace.entity.type Publication
local.contributor.corporatename College of Computing
local.contributor.corporatename School of Computer Science
local.contributor.corporatename Undergraduate Research Opportunities Program
local.relation.ispartofseries Undergraduate Research Option Theses
relation.isOrgUnitOfPublication c8892b3c-8db6-4b7b-a33a-1b67f7db2021
relation.isOrgUnitOfPublication 6b42174a-e0e1-40e3-a581-47bed0470a1e
relation.isOrgUnitOfPublication 0db885f5-939b-4de1-807b-f2ec73714200
relation.isSeriesOfPublication e1a827bd-cf25-4b83-ba24-70848b7036ac
thesis.degree.level Undergraduate
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
DUQUEVANHISSENHOVEN-UNDERGRADUATERESEARCHOPTIONTHESIS-2018.pdf
Size:
259.73 KB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
LICENSE.txt
Size:
3.88 KB
Format:
Plain Text
Description:
Download
Collections
Undergraduate Scholarship