Aprendizaje por refuerzo aplicado a los videojuegos cooperativos
View/Open
Cita com:
hdl:2117/122583
Document typeBachelor thesis
Date2018-07
Rights accessOpen Access
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
Se ha desarrollado un algoritmo que combina el uso de redes neuronales con el algoritmo Q-learning para aprender a jugar con la ayuda de un jugador humano y aprender a cooperar con él para ganar en un videojuego basado en los combates dobles de Pokémon, el cual ha sido creado des de cero. An algorithm has been developed that combines the use of neural networks with the Q-learning algorithm to learn to play with the help of a human player and to learn to cooperate with him to win a videogame based on Pokémon's double combat, which has been developed from scratch.
SubjectsMachine learning, Neural networks (Computer science), Reinforcement learning, Video games, Aprenentatge automàtic, Xarxes neuronals (Informàtica), Aprenentatge per reforç, Videojocs
DegreeGRAU EN ENGINYERIA INFORMÀTICA (Pla 2010)
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
134359.pdf | 2,012Mb | View/Open |