Evaluating strategies for generalized bandit problems

DOI10.1080/00207728808964060zbMath0648.93072OpenAlexW2013567575MaRDI QIDQ3794055

N. A. Fay, Kevin D. Glazebrook

Publication date: 1988

Published in: International Journal of Systems Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/00207728808964060

zbMATH Keywords

optimal strategybandit problemsoptimal rewardsresearch planning

Mathematics Subject Classification ID

Deterministic scheduling theory in operations research (90B35) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40)

Related Items (4)

Zero-sum Games for Discrete-time Multi-armed Bandit Processes with a Generalized Discount ⋮ New results for generalized bandit problems ⋮ A General Model for the Scheduling of Alternative Stochastic Jobs that may Fail ⋮ On scheduling influential stochastic tasks on a single machine

Cites Work

• On the scheduling of alternative stochastic jobs on a single machine
• Resource allocation in speculative chemical research
• Unnamed Item
• Unnamed Item

This page was built for publication: Evaluating strategies for generalized bandit problems