A revised approach for risk-averse multi-armed bandits under CVaR criterion

DOI10.1016/j.orl.2021.05.005OpenAlexW3160157623MaRDI QIDQ2060576

Yilin Xue, Najakorn Khajonchotpanya, Napat Rujeerapaiboon

Publication date: 13 December 2021

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.orl.2021.05.005

zbMATH Keywords

conditional value-at-riskregret analysisonline learning and bandits

Mathematics Subject Classification ID

Computer science (68-XX) Game theory, economics, finance, and other social and behavioral sciences (91-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
• The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality
• Asymptotically efficient adaptive allocation rules
• Large deviations bounds for estimating conditional value-at-risk
• Dynamic Assortment with Demand Learning for Seasonal Consumer Goods
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Probability Inequalities for Sums of Bounded Random Variables
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Finite-time analysis of the multiarmed bandit problem