An online algorithm for the risk-aware restless bandit

DOI10.1016/j.ejor.2020.08.028zbMath1487.90634OpenAlexW3081812122MaRDI QIDQ2029383

Jianyu Xu, Ou Tang, Lujie Chen

Publication date: 3 June 2021

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ejor.2020.08.028

zbMATH Keywords

Markov processrisk measureonline optimizationmulti-armed banditrisk-aware

Mathematics Subject Classification ID

Statistical methods; risk measures (91G70) Markov and semi-Markov decision processes (90C40)

Related Items (1)

A tractable online learning algorithm for the multinomial logit contextual bandit

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Regret bounds for restless Markov bandits
• Risk-averse dynamic programming for Markov decision processes
• Eigenvalue bounds on convergence to stationarity for nonreversible Markov chains, with an application to the exclusion process
• General state space Markov chains and MCMC algorithms
• Asymptotically efficient adaptive allocation rules
• Adaptive treatment allocation and the multi-armed bandit problem
• Optimal selection of obsolescence mitigation strategies using a restless bandit model
• Concentration inequalities for Markov chains by Marton couplings and spectral methods
• RISK MEASURES ON P(R) AND VALUE AT RISK WITH PROBABILITY/LOSS FUNCTION
• Optimal Control of Markov Decision Processes With Linear Temporal Logic Constraints
• Online Learning of Rested and Restless Bandits
• Multi‐Armed Bandit Allocation Indices
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
• A Central Limit Theorem and Hypotheses Testing for Risk-averse Stochastic Programs
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Optimality of Myopic Sensing in Multichannel Opportunistic Access
• Sequential Decision Making With Coherent Risk
• Optimization of Convex Risk Functions
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Distributionally Robust Reward-Risk Ratio Optimization with Moment Constraints
• Some aspects of the sequential design of experiments
• On consistency of stochastic dominance and mean-semideviation models
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: An online algorithm for the risk-aware restless bandit