bibtype J - Journal Article
ARLID 0567218
utime 20240402213552.6
mtime 20230120235959.9
SCOPUS 85146315332
WOS 000960827100001
DOI 10.1016/j.orl.2023.01.008
title (primary) (eng) Contractivity of Bellman operator in risk averse dynamic programming with infinite horizon
specification
page_count 4 s.
media_type P
serial
ARLID cav_un_epca*0254574
ISSN 0167-6377
title Operations Research Letters
volume_id 51
volume 2 (2023)
page_num 133-136
publisher
name Elsevier
keyword Risk aversion
keyword Dynamic programming
keyword Infinite horizon
author (primary)
ARLID cav_un_auth*0289084
name1 Kopa
name2 M.
country CZ
author
ARLID cav_un_auth*0101206
name1 Šmíd
name2 Martin
institution UTIA-B
full_dept (cz) Ekonometrie
full_dept Department of Econometrics
department (cz) E
department E
full_dept Department of Econometrics
share 50
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
url http://library.utia.cas.cz/separaty/2023/E/smid-0567218.pdf
source
url https://www.sciencedirect.com/science/article/pii/S0167637723000081?via%3Dihub
cas_special
project
project_id GA19-11062S
agency GA ČR
country CZ
ARLID cav_un_auth*0385133
abstract (eng) The paper deals with a risk averse dynamic programming problem with infinite horizon. First, the required assumptions are formulated to have the problem well defined. Then the Bellman equation is derived, which may be also seen as a standalone reinforcement learning problem. The fact that the Bellman operator is contraction is proved, guaranteeing convergence of various solution algorithms used for dynamic programming as well as reinforcement learning problems, which we demonstrate on the value iteration and the policy iteration algorithms.
result_subspec WOS
RIV BB
FORD0 10000
FORD1 10100
FORD2 10103
reportyear 2024
num_of_auth 2
inst_support RVO:67985556
permalink https://hdl.handle.net/11104/0340876
confidential S
mrcbC91 C
mrcbT16-e OPERATIONSRESEARCHMANAGEMENTSCIENCE
mrcbT16-j 0.502
mrcbT16-D Q4
arlyear 2023
mrcbU14 85146315332 SCOPUS
mrcbU24 PUBMED
mrcbU34 000960827100001 WOS
mrcbU63 cav_un_epca*0254574 Operations Research Letters Roč. 51 č. 2 2023 133 136 0167-6377 1872-7468 Elsevier