Texto completo
Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (836kB) | Vista Previa |
Q-Learning based control algorithm for HTTP adaptive streaming
Cita
Martín Gutiérrez, Virginia, Cabrera Quesada, Julian 
ORCID: https://orcid.org/0000-0002-7154-2451 and García Santos, Narciso ORCID: https://orcid.org/0000-0002-0397-894X
(2015).
Q-Learning based control algorithm for HTTP adaptive streaming.
En: "Visual Communications and Image Processing (VCIP 2015)", 13/12/2015 - 16/12/2015, Singapore. pp. 1-4.
https://doi.org/10.1109/VCIP.2015.7457906.
ORCID: https://orcid.org/0000-0002-7154-2451 and García Santos, Narciso ORCID: https://orcid.org/0000-0002-0397-894X
(2015).
Q-Learning based control algorithm for HTTP adaptive streaming.
En: "Visual Communications and Image Processing (VCIP 2015)", 13/12/2015 - 16/12/2015, Singapore. pp. 1-4.
https://doi.org/10.1109/VCIP.2015.7457906.
Descripción
| Título: | Q-Learning based control algorithm for HTTP adaptive streaming |
|---|---|
| Autor/es: |
|
| Tipo de Documento: | Ponencia en Congreso o Jornada (Artículo) |
| Título del Evento: | Visual Communications and Image Processing (VCIP 2015) |
| Fechas del Evento: | 13/12/2015 - 16/12/2015 |
| Lugar del Evento: | Singapore |
| Título del Libro: | Visual Communications and Image Processing (VCIP 2015) |
| Fecha: | 2015 |
| Materias: | |
| ODS: | |
| Palabras Clave Informales: | HTTP Adaptive Streaming, reinforcement learning, state, reward, policy, adaptation, Quality of Experience |
| Escuela: | E.T.S.I. Telecomunicación (UPM) |
| Departamento: | Señales, Sistemas y Radiocomunicaciones |
| Licencias Creative Commons: | Reconocimiento - Sin obra derivada - No comercial |
Resumen
We present a control algorithm based on Q-Learning for an HTTP Adaptive Streaming (HAS) Client in order to optimize the Quality of Experience (QoE) of the user. First, we propose a model with a suitable number of variables in an attempt to find a reasonable tradeoff between the complexity of the model and its capacity to capture appropriately the dynamics of the system. Second, we define a novel reward function that takes into consideration factors related to the user's QoE. Results will show, that our Q-learning algorithm is able to learn and efficiently control the selection of the segment qualities. In addition, we will show that our proposed approach outperforms another Q-learning approach.
Proyectos asociados
Tipo
Código
Acrónimo
Responsable
Título
Gobierno de España
TEC2013-48453
MR-UHDTV
Ministerio de Economía y Competitividad
Sin especificar
Gobierno de España
ITEA2-11012
ICARE
Ministerio de Economía y Competitividad
Sin especificar
Gobierno de España
IPT-2012-0306-430000
Videocells
Ministerio de Economía y Competitividad
Sin especificar
Más información
| ID de Registro: | 42757 |
|---|---|
| Identificador DC: | https://oa.upm.es/42757/ |
| Identificador OAI: | oai:oa.upm.es:42757 |
| Identificador DOI: | 10.1109/VCIP.2015.7457906 |
| Depositado por: | Memoria Investigacion |
| Depositado el: | 16 Jul 2016 09:46 |
| Ultima Modificación: | 16 Jul 2016 09:46 |
Acciones
- Estadísticas
- Exportar cita
- Editar (sólo personal del Archivo)
