Observatorio de I+D+i UPM

Descripción
We extend previous works on stochastic dynamic potential games (DPGs) with constrained continuous state-action spaces, and present a closed-loop analysis when the players are forced to use parametric policies. Our main assumption is that the parameter space must be finite-dimensional. We show that a closed-loop Nash equilibrium of a DPG can be found by solving a related optimal control problem (OCP). This is convenient since solving a single OCP (which is a single-objective problem) is usually much simpler than solving the original set of coupled OCPs that form the game (which is a multiobjective problem).
Internacional	Si
Nombre congreso	Learning, Inference and Control of Multi-Agent Systems Workshop on Neural Information Processing (NIPS)
Tipo de participación	970
Lugar del congreso	Barcelona
Revisores	Si
ISBN o ISSN
DOI
Fecha inicio congreso	10/12/2016
Fecha fin congreso	10/12/2016
Desde la página	1
Hasta la página	6
Título de las actas

Esta actividad pertenece a memorias de investigación

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

• Creador: Grupo de Investigación: Grupo de Aplicaciones del Procesado de Señal (GAPS)