Exploring how different state representations and configurations affect the learning process and outcome of deep Q-learning algorithms

URI: http://hdl.handle.net/1992/14977

URL: http://biblioteca.uniandes.edu.co/acepto201699.php?id=11391.pdf

Author: Montoya Sefair, Diego

Director(s)/Advisor(s): Takahashi Rodríguez, Silvia

Publication date: 2016

Content type: bachelorThesis

Keywords:

Aprendizaje por refuerzo (Aprendizaje automático) - Investigaciones

Redes neurales (Computadores) - Investigaciones

Show full item record

Files in this item

Name:

u754239.pdf

Size:

2.034Mb

Format:

PDF

Statistics

View Usage Statistics