Contractivity of Bellman operator in risk averse dynamic programming with infinite horizon

0567218 - ÚTIA 2024 RIV NL eng J - Článek v odborném periodiku
Kopa, M. - Šmíd, Martin
Contractivity of Bellman operator in risk averse dynamic programming with infinite horizon.
Operations Research Letters. Roč. 51, č. 2 (2023), s. 133-136. ISSN 0167-6377. E-ISSN 1872-7468
Grant CEP: GA ČR(CZ) GA19-11062S
Institucionální podpora: RVO:67985556
Klíčová slova: Risk aversion * Dynamic programming * Infinite horizon
Obor OECD: Statistics and probability
Impakt faktor: 1.1, rok: 2022
Způsob publikování: Omezený přístup
http://library.utia.cas.cz/separaty/2023/E/smid-0567218.pdf https://www.sciencedirect.com/science/article/pii/S0167637723000081?via%3Dihub

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.
Trvalý link: https://hdl.handle.net/11104/0340876