Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ RUIdeRAarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
RUIdeRA
Article . 2018
Data sources: RUIdeRA
addClaim

VAR: Visualización de Técnicas de Aprendizaje por Refuerzo.

Authors: Martín Izquierdo, Eduardo;

VAR: Visualización de Técnicas de Aprendizaje por Refuerzo.

Abstract

En la actualidad, la Inteligencia Artificial cada vez va cogiendo más peso en nuestra sociedad, llegando al posible punto en el que sean capaces de sustituir a los humanos en la mayoría de los trabajos. Esa capacidad de aprender actividades, con una eficiencia y rapidez mayor que los humanos, es gracias al Aprendizaje por Refuerzo, un área del Aprendizaje Automático. En este trabajo se muestra una visualización de los conceptos básicos del Aprendizaje por Refuerzo, donde se espera que el usuario pueda apreciar lo potente y alucinante que puede ser el proceso de aprendizaje llevado a cabo por un agente. Por lo tanto, se demuestra que el algoritmo QL junto a un agente pueden dar lugar a aplicaciones muy fructíferas en el futuro.

Nowadays, Artificial Intelligence is increasingly taking on more weight in our society, reaching the posible point where it can replace humans in most of the jobs. This ability to learn activities, with a greater efficiency and speed than humans, is of because Reinforcement Learning, an area of Machine Learning. In this project, a visualization of the main conceps of Reinforcement Learining is shown, where it’s expected that the user could appreciate how powerful and amazing the learning process carried out by an agent can be. Therefore, it is demonstrated that the QL algorithm together with an agent can lead to very fruitful applications in the future.

Country
Spain
Related Organizations
Keywords

Informática, Aplicación informática

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green