Decision Processes with Total-Cost Criteria
Demko, Stephen ; Hill, Theodore P.
Ann. Probab., Tome 9 (1981) no. 6, p. 293-301 / Harvested from Project Euclid
By a decision process is meant a pair $(X, \Gamma)$, where $X$ is an arbitrary set (the state space), and $\Gamma$ associates to each point $x$ in $X$ an arbitrary nonempty collection of discrete probability measures (actions) on $X$. In a decision process with nonnegative costs depending on the current state, the action taken, and the following state, there is always available a Markov strategy which uniformly (nearly) minimizes the expected total cost. If the costs are strictly positive and depend only on the current state, there is even a stationary strategy with the same property. In a decision process with a fixed goal $g$ in $X$, there is always a stationary strategy which uniformly (nearly) minimizes the expected time to the goal, and, if $X$ is countable, such a stationary strategy exists which also (nearly) maximizes the probability of reaching the goal.
Publié le : 1981-04-14
Classification:  Gambling theory,  dynamic programming,  decision theory,  stationary strategy,  Markov strategy,  total-cost criteria,  60G99,  62C05
@article{1176994470,
     author = {Demko, Stephen and Hill, Theodore P.},
     title = {Decision Processes with Total-Cost Criteria},
     journal = {Ann. Probab.},
     volume = {9},
     number = {6},
     year = {1981},
     pages = { 293-301},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176994470}
}
Demko, Stephen; Hill, Theodore P. Decision Processes with Total-Cost Criteria. Ann. Probab., Tome 9 (1981) no. 6, pp.  293-301. http://gdmltest.u-ga.fr/item/1176994470/