| bibtype |
J -
Journal Article
|
| ARLID |
0399560 |
| utime |
20240903170627.7 |
| mtime |
20131203235959.9 |
| SCOPUS |
84889006605 |
| WOS |
000328665200004 |
| title
(primary) (eng) |
Approximate Dynamic Programming Based on High Dimensional Model Representation |
| specification |
| page_count |
18 s. |
| media_type |
P |
|
| serial |
| ARLID |
cav_un_epca*0297163 |
| ISSN |
0023-5954 |
| title
|
Kybernetika |
| volume_id |
49 |
| volume |
5 (2013) |
| page_num |
720-737 |
| publisher |
| name |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
|
| keyword |
approximate dynamic programming |
| keyword |
Bellman equation |
| keyword |
approximate HDMR minimization |
| keyword |
trust region problem |
| author
(primary) |
| ARLID |
cav_un_auth*0234872 |
| full_dept (cz) |
Matematická teorie rozhodování |
| full_dept (eng) |
Department of Decision Making Theory |
| department (cz) |
MTR |
| department (eng) |
MTR |
| full_dept |
Department of Decision Making Theory |
| name1 |
Pištěk |
| name2 |
Miroslav |
| institution |
UTIA-B |
| fullinstit |
Ústav teorie informace a automatizace AV ČR, v. v. i. |
|
| source |
|
| cas_special |
| project |
| ARLID |
cav_un_auth*0273082 |
| project_id |
GAP102/11/0437 |
| agency |
GA ČR |
| country |
CZ |
|
| abstract
(eng) |
This article introduces an algorithm for implicit High Dimensional Model Representation (HDMR) of the Bellman equation. This approximation technique reduces memory demands of the algorithm considerably. Moreover, we show that HDMR enables fast approximate min- imization which is essential for evaluation of the Bellman function. In each time step, the problem of parametrized HDMR minimization is relaxed into trust region problems, all sharing the same matrix. Finding its eigenvalue decomposition, we effectively achieve estimates of all minima. Their full-domain representation is avoided by HDMR and then the same approach is used recursively in the next time step. An illustrative example of N-armed bandit problem is included. We assume that the newly established connection between approximate HDMR minimization and the trust region problem can be beneficial also to many other applications. |
| RIV |
BC |
| reportyear |
2014 |
| mrcbC52 |
4 O 4o 20231122135935.5 |
| inst_support |
RVO:67985556 |
| permalink |
http://hdl.handle.net/11104/0226953 |
| mrcbT16-e |
COMPUTERSCIENCECYBERNETICS |
| mrcbT16-f |
0.577 |
| mrcbT16-g |
0.098 |
| mrcbT16-h |
9.IV |
| mrcbT16-i |
0.00191 |
| mrcbT16-j |
0.341 |
| mrcbT16-k |
655 |
| mrcbT16-l |
61 |
| mrcbT16-s |
0.348 |
| mrcbT16-z |
ScienceCitationIndexExpanded |
| mrcbT16-4 |
Q2 |
| mrcbT16-B |
35.159 |
| mrcbT16-C |
31.250 |
| mrcbT16-D |
Q3 |
| mrcbT16-E |
Q3 |
| arlyear |
2013 |
| mrcbTft |
\nSoubory v repozitáři: pistek-0399560.pdf |
| mrcbU14 |
84889006605 SCOPUS |
| mrcbU34 |
000328665200004 WOS |
| mrcbU63 |
cav_un_epca*0297163 Kybernetika 0023-5954 Roč. 49 č. 5 2013 720 737 Ústav teorie informace a automatizace AV ČR, v. v. i. |
|