Algorithms for evaluating the dynamic allocation index

DOI10.1016/0167-6377(82)90050-5zbMath0488.90074OpenAlexW1989992646MaRDI QIDQ1166434

S. Singh

Publication date: 1982

Published in: Operations Research Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0167-6377(82)90050-5

zbMATH Keywords

algorithmstwo-armed bandit problemoptimal policiesmulti-armed bandit problemdynamic allocation indicesalternative bandit processescalculation of indicesMarkov decision chain

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (8)

Stochastic scheduling and forwards induction ⋮ Index policy for multiarmed bandit problem with dynamic risk measures ⋮ Algorithms for evaluating the dynamic allocation index ⋮ Stochastic scheduling: a short history of index policies and new approaches to index generation for dynamic resource allocation ⋮ A comparative study of ad hoc techniques and evolutionary methods for multi-armed bandit problems ⋮ Un ordonnancement dynamique de tâches stochastiques sur un seul processeur ⋮ Robust control of the multi-armed bandit problem ⋮ Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges

Cites Work

• Algorithms for evaluating the dynamic allocation index
• Unnamed Item

This page was built for publication: Algorithms for evaluating the dynamic allocation index