Mean, variance and probabilistic criteria in finite Markov decision processes: A review (Q1821706): Difference between revisions
From MaRDI portal
Created a new Item |
Added link to MaRDI item. |
||
links / mardi / name | links / mardi / name | ||
Revision as of 10:46, 1 February 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Mean, variance and probabilistic criteria in finite Markov decision processes: A review |
scientific article |
Statements
Mean, variance and probabilistic criteria in finite Markov decision processes: A review (English)
0 references
1988
0 references
This paper is a survey of papers which make use of nonstandard Markov decision process criteria (i.e., those which do not seek simply to optimize expected returns per unit time or expected discounted return). It covers infinite-horizon nondiscounted formulations, infinite-horizon discounted formulations, and finite-horizon formulations. For problem formulations in terms solely of the probabilities of being in each state and taking each action, policy equivalence results are given which allow policies to be restricted to the class of Markov policies or to the randomizations of deterministic Markov policies. For problems which cannot be stated in such terms, in terms of the primitive state set I, formulations involving a redefinition of the states are examined.
0 references
survey
0 references
nonstandard Markov decision process criteria
0 references
infinite-horizon nondiscounted formulations
0 references
discounted formulations
0 references
finite-horizon
0 references
mean
0 references
variance
0 references
probabilistic criteria
0 references