Memorias de investigación
Communications at congresses:
Closed-Loop Stochastic Dynamic Potential Games with Parametric Policies and Constraints
Year:2016

Research Areas
  • Game theory,
  • Processing and signal analysis,
  • Adaptive control

Information
Abstract
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).
International
Si
Congress
Learning, Inference and Control of Multi-Agent Systems Workshop on Neural Information Processing (NIPS)
970
Place
Barcelona
Reviewers
Si
ISBN/ISSN
Start Date
10/12/2016
End Date
10/12/2016
From page
1
To page
6
Participants

Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Aplicaciones del Procesado de Señal (GAPS)