Texto completo
![[thumbnail of INVE_MEM_2013_166647.pdf]](https://oa.upm.es/style/images/fileicons/application_pdf.png) Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (851kB) |
Cooperative off-policy prediction of markov decision processes in adaptive networks
Cita
Valcarcel Macua, Sergio, Chen, Jianshu, Zazo Bello, Santiago 
ORCID: https://orcid.org/0000-0001-9073-7927 and Sayed, Ali H.
(2013).
Cooperative off-policy prediction of markov decision processes in adaptive networks.
En: "IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)", 26/05/2013 - 31/05/2013, Vancouver, Canada. pp. 4539-4543.
https://doi.org/10.1109/ICASSP.2013.6638519.
ORCID: https://orcid.org/0000-0001-9073-7927 and Sayed, Ali H.
(2013).
Cooperative off-policy prediction of markov decision processes in adaptive networks.
En: "IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)", 26/05/2013 - 31/05/2013, Vancouver, Canada. pp. 4539-4543.
https://doi.org/10.1109/ICASSP.2013.6638519.
Descripción
| Título: | Cooperative off-policy prediction of markov decision processes in adaptive networks |
|---|---|
| Autor/es: |
|
| Tipo de Documento: | Ponencia en Congreso o Jornada (Artículo) |
| Título del Evento: | IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) |
| Fechas del Evento: | 26/05/2013 - 31/05/2013 |
| Lugar del Evento: | Vancouver, Canada |
| Título del Libro: | IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) |
| Fecha: | 2013 |
| Materias: | |
| ODS: | |
| Escuela: | E.T.S.I. Telecomunicación (UPM) |
| Departamento: | Señales, Sistemas y Radiocomunicaciones |
| Licencias Creative Commons: | Reconocimiento - Sin obra derivada - No comercial |
Resumen
We apply diffusion strategies to propose a cooperative reinforcement learning algorithm, in which agents in a network communicate with their neighbors to improve predictions about their environment. The algorithm is suitable to learn off-policy even in large state spaces. We provide a mean-square-error performance analysis under constant step-sizes. The gain of cooperation in the form of more stability and less bias and variance in the prediction error, is illustrated in the context of a classical model. We show that the improvement in performance is especially significant when the behavior policy of the agents is different from the target policy under evaluation.
Más información
| ID de Registro: | 28941 |
|---|---|
| Identificador DC: | https://oa.upm.es/28941/ |
| Identificador OAI: | oai:oa.upm.es:28941 |
| Identificador DOI: | 10.1109/ICASSP.2013.6638519 |
| Depositado por: | Memoria Investigacion |
| Depositado el: | 29 Jun 2014 11:38 |
| Ultima Modificación: | 22 Sep 2014 11:43 |
Acciones
- Estadísticas
- Exportar cita
- Editar (sólo personal del Archivo)
