Risk-Sensitive and Risk-Neutral Multiarmed Bandits

DOI10.1287/MOOR.1060.0240MaRDI QIDQ5388036zbMATH OpenOpenAlexFDO

Authors Eric V. Denardo, Haechurl Park, Uriel G. Rothblum

Publication date 27 May 2008

Published in Mathematics of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1287/moor.1060.0240

zbMATH Keywords

exponential utilitymultiarmed banditsoptimal stoppingrisk-sensitive Markov decision processes

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• The multi-armed bandit, with constraints
• The Multi-Armed Bandit Problem: Decomposition and Computation
• Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality
• scientific article; zbMATH DE number 4059270
• scientific article; zbMATH DE number 3891095

Cited in

(21)

• Risk aversion in expected intertemporal discounted utilities bandit problems
• An online algorithm for the risk-aware restless bandit
• A revised approach for risk-averse multi-armed bandits under CVaR criterion
• Robust risk-averse stochastic multi-armed bandits
• Constant risk aversion in stochastic contests with exponential completion times
• On the reduction of total-cost and average-cost MDPs to discounted mdps
• Four proofs of Gittins' multiarmed bandit theorem
• The multi-armed bandit, with constraints
• Optimal halting policies in Markov population decision chains with constant risk posture
• Game of thrones: fully distributed learning for multiplayer bandits
• Minimax Off-Policy Evaluation for Multi-Armed Bandits
• Open bandit processes with uncountable states and time-backward effects
• ON THE IDENTIFICATION AND MITIGATION OF WEAKNESSES IN THE KNOWLEDGE GRADIENT POLICY FOR MULTI-ARMED BANDITS
• Optimal activation of halting multi‐armed bandit models
• Index policy for multiarmed bandit problem with dynamic risk measures
• Multi-armed bandits with censored consumption of resources
• Approximate solutions to constrained risk-sensitive Markov decision processes
• Markov decision processes with risk-sensitive criteria: an overview
• An exact bandit model for the risk-volatility tradeoff
• Optimizing sequential decision-making under risk: strategic allocation with switching penalties
• Stochastic scheduling in an in-forest

This page was built for publication: Risk-Sensitive and Risk-Neutral Multiarmed Bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5388036)