Applying deep reinforcement learning to Berkeley's capture the flag game
"This project aimed to apply Deep Reinforcement Learning methods on Capture the Flag, a game designed for Berkeley's Introduction to AI (CS188) class. Furthermore, the potential of generating images from the state information of the game and using these as inputs to a Deep Neural Network w...
- Autores:
-
Rojas Herrera, Santiago
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2019
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/39251
- Acceso en línea:
- http://hdl.handle.net/1992/39251
- Palabra clave:
- Aprendizaje por refuerzo (Aprendizaje automático)
Agentes inteligentes (Programas para computador)
Redes neurales (Computadores)
Ingeniería
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| Summary: | "This project aimed to apply Deep Reinforcement Learning methods on Capture the Flag, a game designed for Berkeley's Introduction to AI (CS188) class. Furthermore, the potential of generating images from the state information of the game and using these as inputs to a Deep Neural Network was studied. Then, multiple agents that used different exploring strategies and different reward functions were trained, with the purpose of finding the most effective way to train agents for this game."--Tomado del Formato de Documento de Grado. |
|---|