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/ Recolector de Cienci...arrow_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/
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/
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/
Biblos-e Archivo
Bachelor thesis . 2021
Data sources: Biblos-e Archivo
versions View all 3 versions
addClaim

Aprendizaje por refuerzo profundo con OpenAI Gym

Authors: García Pascual, Mario;

Aprendizaje por refuerzo profundo con OpenAI Gym

Abstract

El Aprendizaje por refuerzo profundo (DRL) surge de la inserción de métodos de Aprendizaje profundo (DL) en los algoritmos de Aprendizaje por refuerzo (RL). A pesar de los hitos logrados en este campo durante los últimos años, sigue ocupando un estatus de nicho en el panorama del Aprendizaje automático (ML), y apenas se ha nombrado durante el grado. El objetivo de este trabajo es partir de un estudio del RL clásico para terminar haciendo un estudio detallado de los principales algoritmos de DRL. Luego, hacemos una comparativa del rendimiento de los algoritmos en entornos de OpenAI Gym. El primer algoritmo de DRL que estudiamos es Deep Q-Network (DQN), que logra fusionar por primera vez RL y DL con éxito. Luego, investigamos sus tres extensiones más conocidas: Double Deep Q-Network (DDQN), Dueling Network y Prioritized Experience Replay (PER). Finalmente, introducimos una familia distinta de algoritmos con el estudio de Advantage Actor-Critic (A2C), que trata de resolver el mismo problema con un enfoque diferente. La comparativa la hacemos en cuatro entornos clásicos de OpenAI Gym y usando la librería Stable Baselines. Concluimos que, en los entornos sencillos que probamos, no se percibe la diferencia entre DQNysus extensiones. Por último, comprobamos que las mejoras que introdujo DQN son relevantes, desactivándolas y viendo que no logra aprender.

Country
Spain
Related Organizations
Keywords

Informática, Aprendizaje por refuerzo profundo, Aprendizaje por refuerzo, Aprendizaje automático

  • 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