Asymptotically optimal strategies for adaptive zero-sum discounted markov games

J. Adolfo Minjárez-Sosa, Oscar Vega-Amaya*

*Autor correspondiente de este trabajo

Producción científica: Contribución a una revistaArtículorevisión exhaustiva

10 Citas (Scopus)

Resumen

We consider a class of discrete-time two person zero-sum Markov games with Borel state and action spaces, and possibly unbounded payoffs. The ga me evolves according to the recursive equation xn+1 = F(xn,a n,bn,n), n = 0, 1,..., where the disturbance process {n} is formed by independent and identically distributed Rk-valued random vectors, which are observable but whose common density p is unknown to both players. Under certain continuity and compactness conditions, we combine a nonstationary iteration procedure and suitable den sity estimation methods to construct asymptotically discounted optimal strategies for both players.

Idioma originalInglés
Páginas (desde-hasta)1405-1421
Número de páginas17
PublicaciónSIAM Journal on Control and Optimization
Volumen48
N.º3
DOI
EstadoPublicada - 2009

Huella

Profundice en los temas de investigación de 'Asymptotically optimal strategies for adaptive zero-sum discounted markov games'. En conjunto forman una huella única.

Citar esto