Graph representations for reinforcement learning

dc.creatorSchab, Esteban Alejandro
dc.creatorCasanova Pietroboni, Carlos Antonio
dc.creatorPiccoli, María Fabiana
dc.creator.orcid0000-0002-2142-2187
dc.creator.orcid0000-0002-3636-7360
dc.date.accessioned2024-12-27T15:06:20Z
dc.date.issued2024-04
dc.description.abstractGraph analysis is becoming increasingly important due to the expressive power of graph models and the efficient algorithms available for processing them. Reinforcement Learning is one domain that could ben- efit from advancements in graph analysis, given that a learning agent may be integrated into an environ- ment that can be represented as a graph. Nevertheless, the structural irregularity of graphs and the lack of prior labels make it difficult to integrate such a model into modern Reinforcement Learning frameworks that rely on artificial neural networks. Graph embedding enables the learning of low-dimensional vector representations that are more suited for machine learning algorithms, while retaining essential graph features. This paper presents a framework for evaluating graph embedding algorithms and their ability to preserve the structure and relevant features of graphs by means of an internal validation metric, without resorting to subsequent tasks that require labels for training. Based on this framework, three defined algorithms that meet the necessary requirements for solving a specific problem of Reinforcement Learningin graphs are selected, analyzed, and compared. These algorithms are Graph2Vec, GL2Vec, and Wavelet Characteristics, with the latter two demonstrating superior performance.
dc.description.affiliationFil: Schab, Esteban Alejandro. Universidad Tecnológica Nacional. Facultad Regional Concepción del Uruguay. Departamento Ingeniería en Sistemas de Información. Grupo de Investigación Inteligencia Computacional e Ingeniería de Software; Argentina.
dc.description.affiliationFil: Casanova Pietroboni, Carlos Antonio. Universidad Tecnológica Nacional. Facultad Regional Concepción del Uruguay. Departamento Ingeniería en Sistemas de Información. Grupo de Investigación Inteligencia Computacional e Ingeniería de Software; Argentina.
dc.description.affiliationFil: Casanova Pietroboni, Carlos Antonio. Universidad Autónoma de Entre Ríos; Argentina.
dc.description.affiliationFil: Piccoli, María Fabiana. Universidad Nacional de San Luis; Argentina.
dc.description.affiliationFil: Piccoli, María Fabiana. Universidad Autónoma de Entre Ríos; Argentina.
dc.formatpdf
dc.identifier.citationJournal of Computer Science and Technology
dc.identifier.doihttps://doi.org/10.24215/16666038.24.e03
dc.identifier.issn1666-6038
dc.identifier.urihttp://hdl.handle.net/20.500.12272/12050
dc.language.isoen
dc.publisherUniversidad Nacional de La Plata. Facultad de Informática.
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 Internationalen
dc.rights.holderSchab, Esteban Alejandro ; Casanova Pietroboni, Carlos Antonio ; Piccoli, María Fabiana.
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.useNo comercial con fines académicos. Licencia Creative Commons CC BY-NC-SA.
dc.sourceJournal of Computer Science and Technology, 24(1), 29-38. (2024)
dc.subjectComputational intelligence
dc.subjectReinforce- ment learning
dc.subjectGraph embeddings
dc.subjectUnsupervised GRL
dc.subjectWhole graph embedding
dc.titleGraph representations for reinforcement learning
dc.typeinfo:eu-repo/semantics/article
dc.type.versionpublisherVersion

Files

Original bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
2024 - Graph Representations.pdf
Size:
842.78 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
3.63 KB
Format:
Item-specific license agreed upon to submission
Description: