The search session has expired. Please query the service again.

The search session has expired. Please query the service again.

The search session has expired. Please query the service again.

The search session has expired. Please query the service again.

Page 1

Displaying 1 – 5 of 5

Showing per page

Nash ϵ -equilibria for stochastic games with total reward functions: an approach through Markov decision processes

Francisco J. González-Padilla, Raúl Montes-de-Oca (2019)

Kybernetika

The main objective of this paper is to find structural conditions under which a stochastic game between two players with total reward functions has an ϵ -equilibrium. To reach this goal, the results of Markov decision processes are used to find ϵ -optimal strategies for each player and then the correspondence of a better answer as well as a more general version of Kakutani’s Fixed Point Theorem to obtain the ϵ -equilibrium mentioned. Moreover, two examples to illustrate the theory developed are presented....

Nonparametric adaptive control for discrete-time Markov processes with unbounded costs under average criterion

J. Minjárez-Sosa (1999)

Applicationes Mathematicae

We introduce average cost optimal adaptive policies in a class of discrete-time Markov control processes with Borel state and action spaces, allowing unbounded costs. The processes evolve according to the system equations x t + 1 = F ( x t , a t , ξ t ) , t=1,2,..., with i.i.d. k -valued random vectors ξ t , which are observable but whose density ϱ is unknown.

Note on stability estimation in average Markov control processes

Jaime Martínez Sánchez, Elena Zaitseva (2015)

Kybernetika

We study the stability of average optimal control of general discrete-time Markov processes. Under certain ergodicity and Lipschitz conditions the stability index is bounded by a constant times the Prokhorov distance between distributions of random vectors determinating the “original and the perturbated” control processes.

Currently displaying 1 – 5 of 5

Page 1