Index policy for multiarmed bandit problem with dynamic risk measures
Year of publication: |
2024
|
---|---|
Authors: | Malekipirbazari, Milad ; Çavuş, Özlem |
Published in: |
European journal of operational research : EJOR. - Amsterdam [u.a.] : Elsevier, ISSN 0377-2217, ZDB-ID 1501061-2. - Vol. 312.2024, 2 (16.1.), p. 627-640
|
Subject: | Dynamic coherent risk measures | Gittins index | Multiarmed bandit problem | Risk-averse control | Stochastic programming | Theorie | Theory | Stochastischer Prozess | Stochastic process | Risiko | Risk | Risikomaß | Risk measure | Messung | Measurement | Portfolio-Management | Portfolio selection | Mathematische Optimierung | Mathematical programming | Dynamische Optimierung | Dynamic programming | Entscheidung unter Risiko | Decision under risk | Risikoaversion | Risk aversion |
-
Optimizing sequential decision-making under risk : strategic allocation with switching penalties
Malekipirbazari, Milad, (2025)
-
Risk neutral reformulation approach to risk averse stochastic programming
Liu, Rui Peng, (2020)
-
Risk measurement and risk-averse control of partially observable discrete-time Markov systems
Fan, Jingnan, (2018)
- More ...
-
Feature selection using stochastic approximation with Barzilai and Borwein non-monotone gains
Aksakalli, Vural, (2021)
-
Optimizing sequential decision-making under risk : strategic allocation with switching penalties
Malekipirbazari, Milad, (2025)
-
Computational methods for risk-averse undiscounted transient Markov models
Çavuş, Özlem, (2014)
- More ...