| bibtype |
J -
Journal Article
|
| ARLID |
0449029 |
| utime |
20240103210937.7 |
| mtime |
20151023235959.9 |
| WOS |
000358811700008 |
| SCOPUS |
84938521589 |
| DOI |
10.1239/jap/1437658607 |
| title
(primary) (eng) |
Sample-Path Optimal Stationary Policies in Stable Markov Decision Chains with Average Reward Criterion |
| specification |
| page_count |
20 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0256875 |
| ISSN |
0021-9002 |
| title
|
Journal of Applied Probability |
| volume_id |
52 |
| volume |
2 (2015) |
| page_num |
419-440 |
| publisher |
| name |
Cambridge University Press |
|
|
| keyword |
Dominated Convergence theorem for the expected average criterion |
| keyword |
Discrepancy function |
| keyword |
Kolmogorov inequality |
| keyword |
Innovations |
| keyword |
Strong sample-path optimality |
| author
(primary) |
| ARLID |
cav_un_auth*0307645 |
| name1 |
Cavazos-Cadena |
| name2 |
R. |
| country |
MX |
| share |
50 |
|
| author
|
| ARLID |
cav_un_auth*0238984 |
| name1 |
Montes-de-Oca |
| name2 |
R. |
| country |
MX |
| share |
25 |
|
| author
|
| ARLID |
cav_un_auth*0101196 |
| name1 |
Sladký |
| name2 |
Karel |
| full_dept (cz) |
Ekonometrie |
| full_dept |
Department of Econometrics |
| department (cz) |
E |
| department |
E |
| institution |
UTIA-B |
| full_dept |
Department of Econometrics |
| share |
25 |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| project_id |
171396 |
| agency |
GA AV ČR |
| country |
CZ |
| ARLID |
cav_un_auth*0307567 |
|
| abstract
(eng) |
This work concerns discrete-time Markov decision chains with denumerable state and compact action sets. Besides standard continuity requirements, the main assumption on the model is that it admits a Lyapunov function m. In this context the average reward criterion is analyzed from the sample-path point of view. The main conclusion is that, if the expected average reward associated to m^2 is finite under any policy, then a stationary policy obtained from the optimality equation in the standard way is sample-path average optimal in a strong sense. |
| reportyear |
2016 |
| RIV |
BC |
| num_of_auth |
3 |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0250631 |
| cooperation |
| ARLID |
cav_un_auth*0320900 |
| name |
Universidad Aut onoma Metropolitana, Campus Iztapalapa, Avenida San Rafael Atlixco #186, Colonia Vicentina, M exico 09340, |
| country |
MX |
|
| confidential |
S |
| mrcbT16-e |
STATISTICSPROBABILITY |
| mrcbT16-j |
0.784 |
| mrcbT16-s |
0.724 |
| mrcbT16-4 |
Q2 |
| mrcbT16-B |
50.157 |
| mrcbT16-C |
34.553 |
| mrcbT16-D |
Q2 |
| mrcbT16-E |
Q2 |
| arlyear |
2015 |
| mrcbU14 |
84938521589 SCOPUS |
| mrcbU34 |
000358811700008 WOS |
| mrcbU63 |
cav_un_epca*0256875 Journal of Applied Probability 0021-9002 1475-6072 Roč. 52 č. 2 2015 419 440 Cambridge University Press |
|