dc.creator | Yanes Luis, Samuel | es |
dc.creator | Gutiérrez Reina, Daniel | es |
dc.creator | Toral, S. L. | es |
dc.date.accessioned | 2021-06-23T13:49:38Z | |
dc.date.available | 2021-06-23T13:49:38Z | |
dc.date.issued | 2021 | |
dc.identifier.citation | Yanes Luis, S., Gutiérrez Reina, D. y Toral Marín, S. (2021). A Dimensional Comparison between Evolutionary Algorithm and Deep Reinforcement Learning Methodologies for Autonomous Surface Vehicles with Water Quality Sensors. Sensors, 21 (8), Article number 2862. | |
dc.identifier.issn | 1424-8220 | es |
dc.identifier.uri | https://hdl.handle.net/11441/114731 | |
dc.description | Article number 2862 | es |
dc.description.abstract | The monitoring of water resources using Autonomous Surface Vehicles with water-quality
sensors has been a recent approach due to the advances in unmanned transportation technology.
The Ypacaraí Lake, the biggest water resource in Paraguay, suffers from a major contamination
problem because of cyanobacteria blooms. In order to supervise the blooms using these on-board
sensor modules, a Non-Homogeneous Patrolling Problem (a NP-hard problem) must be solved
in a feasible amount of time. A dimensionality study is addressed to compare the most common
methodologies, Evolutionary Algorithm and Deep Reinforcement Learning, in different map scales
and fleet sizes with changes in the environmental conditions. The results determined that Deep
Q-Learning overcomes the evolutionary method in terms of sample-efficiency by 50–70% in higher
resolutions. Furthermore, it reacts better than the Evolutionary Algorithm in high space-state actions.
In contrast, the evolutionary approach shows a better efficiency in lower resolutions and needs fewer
parameters to synthesize robust solutions. This study reveals that Deep Q-learning approaches
exceed in efficiency for the Non-Homogeneous Patrolling Problem but with many hyper-parameters
involved in the stability and convergence. | es |
dc.description.sponsorship | Ministerio de Ciencia, innovación y Universidades RTI2018-098964-B-I00 | es |
dc.description.sponsorship | Junta de Andalucía US-1257508 | es |
dc.description.sponsorship | Junta de Andalucía PY18-RE0009 | es |
dc.description.sponsorship | Junta de Andalucía PAIDI TIC 201 | es |
dc.format | application/pdf | es |
dc.format.extent | 30 p. | es |
dc.language.iso | eng | es |
dc.publisher | MDPI | es |
dc.relation.ispartof | Sensors, 21 (8), Article number 2862. | |
dc.rights | Atribución 4.0 Internacional | * |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-nd/4.0/ | |
dc.subject | Unmanned Surface Vehicles | es |
dc.subject | Evolutionary Algorithm | es |
dc.subject | Deep Reinforcement Learning | es |
dc.subject | Machine learning | es |
dc.subject | Intelligent sensor system | es |
dc.title | A Dimensional Comparison between Evolutionary Algorithm and Deep Reinforcement Learning Methodologies for Autonomous Surface Vehicles with Water Quality Sensors | es |
dc.type | info:eu-repo/semantics/article | es |
dcterms.identifier | https://ror.org/03yxnpp24 | |
dc.type.version | info:eu-repo/semantics/publishedVersion | es |
dc.rights.accessRights | info:eu-repo/semantics/openAccess | es |
dc.contributor.affiliation | Universidad de Sevilla. Departamento de Ingeniería Electrónica | es |
dc.relation.projectID | RTI2018-098964-B-I00 | es |
dc.relation.projectID | US-1257508 | es |
dc.relation.projectID | PY18-RE0009 | es |
dc.relation.projectID | PAIDI TIC 201 | es |
dc.relation.publisherversion | https://www.mdpi.com/1424-8220/21/8/2862 | es |
dc.identifier.doi | 10.3390/s21082862 | es |
dc.journaltitle | Sensors | es |
dc.publication.volumen | 21 | es |
dc.publication.issue | 8 | es |
dc.publication.initialPage | Article number 2862 | es |