0567218 20240402213552.620230120235959.9 85146315332 000960827100001 10.1016/j.orl.2023.01.008 4 s. P cav_un_epca*02545740167-6377512 (2023)133-136Elsevier Risk aversion Dynamic programming Infinite horizon cav_un_auth*0289084 Kopa M. CZ cav_un_auth*0101206 Šmíd Martin UTIA-B Ekonometrie Department of Econometrics E E Department of Econometrics 50 Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2023/E/smid-0567218.pdf https://www.sciencedirect.com/science/article/pii/S0167637723000081?via%3Dihub GA19-11062S GA ČR CZ cav_un_auth*0385133 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. WOS BB 10000 10100 10103 2024 2 RVO:67985556 https://hdl.handle.net/11104/0340876 S Article Operations Research Management Science C OPERATIONSRESEARCH&MANAGEMENTSCIENCE 1.1 0.2 13.6 0.00271 0.502 3313 85 0.449 19 0.97 474 Q2 0.800 110 Q4 8 Q4 Q3 0.21 Q4 8 2023 85146315332 SCOPUS PUBMED 000960827100001 WOS cav_un_epca*0254574 Operations Research Letters Roč. 51 č. 2 2023 133 136 0167-6377 1872-7468 Elsevier