Robust control of the multi-armed bandit problem

DOI10.1007/s10479-015-1965-7zbMath1506.90268OpenAlexW3124603229MaRDI QIDQ2095215

Aparupa Das Gupta, Felipe Caro

Publication date: 9 November 2022

Published in: Annals of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10479-015-1965-7

zbMATH Keywords

Bellman equationproject selectionindex policiesmultiarmed banditrobust Markov decision processesuncertain transition matrix

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Robustness in mathematical programming (90C17)

Related Items (2)

Optimal Learning Under Robustness and Time-Consistency ⋮ Computation of weighted sums of rewards for concurrent MDPs

Cites Work

• Unnamed Item
• Robust decomposable Markov decision processes motivated by allocating school budgets
• Four proofs of Gittins' multiarmed bandit theorem
• The multi-armed bandit, with constraints
• Asymptotically efficient adaptive allocation rules
• Arm-acquiring bandits
• Algorithms for evaluating the dynamic allocation index
• Bounded-parameter Markov decision processes
• Lagrangian relaxation and constraint generation for allocation and advanced scheduling
• Optimal adaptive policies for sequential allocation problems
• On the optimality of the Gittins index rule for multi-armed bandits with multiple plays
• A dynamic programming approach to adjustable robust optimization
• Percentile Optimization for Markov Decision Processes with Parameter Uncertainty
• INDEXABILITY OF BANDIT PROBLEMS WITH RESPONSE DELAYS
• The Multi-Armed Bandit Problem: Decomposition and Computation
• Funding Criteria for Research, Development, and Exploration Projects
• Markov Decision Processes with Imprecise Transition Probabilities
• Optimal Adaptive Policies for Markov Decision Processes
• Markovian Decision Processes with Uncertain Transition Probabilities
• The Nonstochastic Multiarmed Bandit Problem
• Robust Markov Decision Processes
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
• Robust Dynamic Programming

This page was built for publication: Robust control of the multi-armed bandit problem