The discounted method and equivalence of average criteria for risk-sensitive Markov decision processes on Borel spaces (Q964743): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Removed claim: author (P16): Item:Q2375461 |
||
Property / author | |||
Property / author: Francisco Sergio Salem-Silva / rank | |||
Revision as of 12:52, 1 March 2024
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | The discounted method and equivalence of average criteria for risk-sensitive Markov decision processes on Borel spaces |
scientific article |
Statements
The discounted method and equivalence of average criteria for risk-sensitive Markov decision processes on Borel spaces (English)
0 references
20 April 2010
0 references
The work concerns discrete-time Markov decision processes evolving on a Borel space. The system is driven by a risk-averse decision maker with a constant risk sensitivity coefficient \(\lambda > 0\), and the performance of a control policy is measured by the (superior limit) risk-sensitive average cost criterion associated with a nonnegative cost function. Under mild (semi-) continuity and compactness conditions, the following problems are studied via the discounted approach: (i) establishing the existence of optimal stationary policies, and (ii) determination of conditions under which the equality of the optimal value functions associated with the inferior limit and superior limit average criteria can be ensured. The approach of the paper relies on standard dynamic programming ideas and on a simple analytical derivation of a Tauberian relation.
0 references
Hölder's inequality
0 references
contractive operators
0 references
generalized Fatou's lemma
0 references
risk-sensitive discount approach
0 references
weak continuity
0 references