Operator Hilbert spaces without the operator approximation property
چکیده
چکیدهای برای این سند ثبت نشده است.
چکیدهای برای این سند ثبت نشده است.
We develop a theory characterizing optimal stopping times for discrete-time ergodic Markov processes with discounted rewards. The theory differs from prior work by its view of per-stage and terminal reward functions as elements of a certain Hilbert space. In addition to a streaml
We develop a theory characterizing optimal stopping times for discrete-time ergodic Markov processes with discounted rewards. The theory di ers from prior work by its view of per-stage and terminal reward functions as elements of a certain Hilbert space. In addition to a streamli