Algoritmo de aprendizaje por refuerzo para el control de un sistema de transporte público
In recent years, the use of Machine Learning techniques has been increasing in almost any technological environment due to the great utility that they can offer. One of these techniques is called Reinforment Learning or Reinforcement Learning (AR), which is used in different environments such as vid...
- Autores:
-
Salcedo Rodríguez, Mateo
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2020
- Institución:
- Universidad de los Andes
- Repositorio:
- Séneca: repositorio Uniandes
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.uniandes.edu.co:1992/51469
- Acceso en línea:
- http://hdl.handle.net/1992/51469
- Palabra clave:
- Transporte público
Algoritmos (Computadores)
Aprendizaje por refuerzo (Aprendizaje automático)
Tiempo de viaje (Ingeniería del tránsito)
Ingeniería
- Rights
- openAccess
- License
- http://creativecommons.org/licenses/by-nc-nd/4.0/
| Summary: | In recent years, the use of Machine Learning techniques has been increasing in almost any technological environment due to the great utility that they can offer. One of these techniques is called Reinforment Learning or Reinforcement Learning (AR), which is used in different environments such as video games or control problems. One of the most interesting uses of this algorithm can be presented in a system such as public transport, where the main objective is to reduce the travel time of users. Taking into account that the space of possible states of the system is quite large, knowing exactly which is the correct action that optimizes the objective of the system for each of the states is a complex task and in many cases impossible, taking into account that the set of states does not have to be known in advance. |
|---|