Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality

DOI10.1214/aoap/1034968239zbMath0862.90127OpenAlexW2037155730MaRDI QIDQ2564701

Michael N. Katehakis, Uriel G. Rothblum

Publication date: 15 January 1997

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoap/1034968239

zbMATH Keywords

multi-armed bandit problemsGittins indicesLaurent expansions

Mathematics Subject Classification ID

Sensitivity, stability, parametric optimization (90C31) Dynamic programming (90C39) Stopping times; optimal stopping problems; gambling theory (60G40) Markov and semi-Markov decision processes (90C40)

Related Items (6)

Optimistic Gittins Indices ⋮ Marginal productivity index policies for scheduling a multiclass delay-/loss-sensitive queue ⋮ Four proofs of Gittins' multiarmed bandit theorem ⋮ Optimal activation of halting multi‐armed bandit models ⋮ MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT ⋮ Gittins Index for Simple Family of Markov Bandit Processes with Switching Cost and No Discounting

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-armed bandits with discount factor near one: The Bernoulli case
• Finite state Markovian decision processes
• Procedures for the evaluation of strategies for resource allocation in a stochastic environment
• The Multi-Armed Bandit Problem: Decomposition and Computation
• Open bandit processes and optimal scheduling of queueing networks
• On the evaluation of suboptimal strategies for families of alternative bandit processes
• Bounds for discounted stochastic scheduling problems
• Discrete Dynamic Programming
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• An Optimality Condition for Discrete Dynamic Programming with no Discounting
• Discrete Dynamic Programming with a Small Interest Rate
• Discrete Dynamic Programming with Sensitive Discount Optimality Criteria

This page was built for publication: Finite state multi-armed bandit problems: Sensitive-discount, average-reward and average-overtaking optimality