DUFOUR, François; PRIETO-RUMEAU, Tomás

Métadonnées

Licence d’utilisation du document

DUFOUR, François
Méthodes avancées d’apprentissage statistique et de contrôle [ASTRAL]
Institut de Mathématiques de Bordeaux [IMB]
Institut Polytechnique de Bordeaux [Bordeaux INP]

PRIETO-RUMEAU, Tomás

Langue

Article de revue

Ce document a été publié dans

Applied Mathematics and Optimization. 2024

Springer Verlag (Germany)

Date de soutenance

2024

Résumé en anglais

We consider a nonzero-sum $N$-player Markov game on an abstract measurable state space with compact metric action spaces. The payoff functions are bounded Caratheodory functions and the transitions of the system are assumed to have a density function satisfying some continuity conditions. The optimality criterion of the players is given by a total expected payoff on an infinite discrete-time horizon. Under the condition that the game model is absorbing, we establish the existence of Markov strategies that are a noncooperative equilibrium in the family of all history-dependent strategies of the players for both the constrained and the unconstrained problems. We obtain, as a particular case of results, the existence of Nash equilibria for discounted constrained and unconstrained game models.< Réduire

Métadonnées

Partager cette publication !

Licence d’utilisation du document

Nash equilibria for total expected reward absorbing Markov games: the constrained and unconstrained cases

Langue

Ce document a été publié dans

Date de soutenance

Résumé en anglais

URI

Origine

Unités de recherche