Optimal strategies for families of alternative bandit processes

DOI10.1109/TAC.1983.1103327zbMath0538.90095OpenAlexW2037436072MaRDI QIDQ3325498

Kevin D. Glazebrook

Publication date: 1983

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/tac.1983.1103327

zbMATH Keywords

optimal policiesdynamic allocation indicesGittins indicesalternative bandit processes

Mathematics Subject Classification ID

Dynamic programming (90C39) Markov and semi-Markov decision processes (90C40) Optimal stopping in statistics (62L15)

Related Items (3)

Multi-armed bandit problem revisited ⋮ Technology diffusion by learning from neighbours ⋮ Un ordonnancement dynamique de tâches stochastiques sur un seul processeur

This page was built for publication: Optimal strategies for families of alternative bandit processes