Observatorio de I+D+i UPM

Descripción
We extend earlier works on continuous potential games to the most general case: stochastic time varying environment, stochastic rewards, non-reduced form and constrained state-action sets. We provide conditions for a Markov Nash equilibrium (MNE) of the game to be equivalent to the solution of a single control problem. Then, we address the problem of learning this MNE when the reward and state transition models are unknown. We follow a reinforcement learning approach and extend previous algorithms for working with constrained state-action subsets of real vector spaces. As an application example, we simulate a network flow optimization model, in which the relays have batteries that deplete with a random factor. The results obtained with the proposed framework are close to optimal.
Internacional	Si
Nombre congreso	IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Tipo de participación	970
Lugar del congreso	Shanghai, China
Revisores	Si
ISBN o ISSN	2379-190X
DOI	10.1109/ICASSP.2016.7472542
Fecha inicio congreso	20/03/2016
Fecha fin congreso	25/05/2017
Desde la página	1
Hasta la página	5
Título de las actas	Acoustics, Speech and Signal Processing (ICASSP), 2016 IEEE International Conference on

Esta actividad pertenece a memorias de investigación

• Autor: Sergio Valcarcel Macua (UPM)
• Autor: Santiago Zazo Bello (UPM)
• Autor: Javier Zazo Ruiz (UPM)

• Creador: Grupo de Investigación: Grupo de Aplicaciones del Procesado de Señal (GAPS)
• Centro o Instituto I+D+i: Centro de I+d+i en Procesado de la Información y Telecomunicaciones
• Departamento: Señales, Sistemas y Radiocomunicaciones