Deep reinforcement learning IA para Starcraft 2
View/Open
Cita com:
hdl:2117/120692
Document typeBachelor thesis
Date2018-06
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
Este proyecto intenta desarrollar agentes de aprendizaje por refuerzo para escenarios concretos de Starcraft 2 y sacar conclusiones sobre cuales son las dificultades más importantes y los enfoques más adecuados para afrontar el reto que supone. This project's goal is to develop reinforcement learning agents for specific scenarios of Starcraft 2 and to draw some conclusions about which are the main difficulties and what are the best approaches to face the challenge that it presents.
SubjectsArtificial intelligence, Reinforcement learning, Intel·ligència artificial, Aprenentatge per reforç
DegreeGRAU EN ENGINYERIA INFORMÀTICA (Pla 2010)
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
134265.pdf | 7,345Mb | View/Open |